Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/icccn58024.2023.10230141

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/icccn58024.2023.10230208

researchmap

researchmap

researchmap

researchmap

researchmap

Publishing type：Research paper (scientific journal)   Publisher：Institute of Electrical and Electronics Engineers (IEEE)  

DOI： 10.1109/access.2021.3133851

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

In recent years, video traffic has rapidly increased, and reducing video traffic is an important issue for network providers. By caching video content at cache servers close to users, network providers can expect to reduce the video traffic in the networks. However, the storage capacity of cache servers is limited, so it is necessary to carefully select contents to be cached to effectively utilize the limited cache resources. In order to make effective use of cache resources, it is important to cache content based on the popularity dynamics of video contents. It is known that video contents have different popularity dynamics in each video category. For example, videos of movie and music categories tend to maintain view counts over long time, whereas the view counts of videos of news and sports categories rapidly decrease. In this paper, we propose a caching method that selects video content to be cached based on the popularity dynamics of video content in each category. To clarify the effectiveness of the proposed caching method, we evaluate the cache hit ratio of the proposed method by a trace-driven simulator using a measured request pattern of YouTube videos. We show that the proposed method improves the cache hit ratio compared with the LRU.

DOI： 10.1109/CCNC46108.2020.9045318

Scopus

researchmap

DOI： 10.1587/transcom.2018EIP0001

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/LANMAN.2019.8846996

researchmap

DOI： 10.1587/transcom.2018EBP3170

researchmap

DOI： 10.1587/transcom.2018EBP3154

researchmap

DOI： 10.1587/transcom.2018EBP3045

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

DOI： 10.1109/GLOCOM.2018.8647130

researchmap

DOI： 10.1587/transcom.2018EBP3043

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

DOI： 10.23919/ICMU.2018.8653625

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE Computer Society  

ICN (Information-Centric Networking) originally innovated for efficient content distribution, is now discussed to be applied to edge computing in IoT (Internet of Things) environment. In this paper, we focus on more flexible network processing environment, in-network processing, which is realized with ICN architecture. In our assumed environment, multiple functions are executed on different routers widely distributed in a whole network and the end-to-end optimal route for any data processing should be selected to satisfy various IoT applications' requirement. Our proposal, an on-demand routing method efficiently chains data and multiple functions compared to an existing proactive routing method. Also, our method reactively caches routing information in the network and realize scalable routing for ICN-based in-network processing.

DOI： 10.1109/LANMAN.2018.8475111

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

ICN (Information-Centric Networking) has been proposed for efficient content distribution to deal with rapid increase of the Internet traffic. This paper proposes a caching and content-Aware routing method named CCAR. CCAR operates based on the ICN concept that users can obtain contents from anywhere in networks. CCAR is formulated as an optimization problem to coordinately perform content placement to caches and content download based on content-oriented traffic engineering. In this paper, after we formulate CCAR, we decompose the problem to a content placement sub-problem and a traffic engineering sub-problem. In the content placement sub-problem, contents are placed at routers by a local search algorithm. The traffic engineering sub-problem calculates routes according to the content placement. Our numerical results show that CCAR efficiently reduces the maximum link utilization and avoids congestion.

DOI： 10.1109/CQR.2018.8445945

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electrical and Electronics Engineers Inc.  

Information-Centric Networking (ICN) has been proposed for efficient content distribution. ICN routers are generally equipped with cache storages and store incoming data packets temporally. In order to leverage as much total cache storages in a network as possible, the combination of routing policy and cache policy installed on the routers is dominant factor for performance. For routing policy, an efficient off-path forwarding method with in-network guidance, Breadcrumbs, has been proposed. In this paper, we propose a cache decision policy based on betweenness centrality and content popularity, which is suitable for Breadcrumbs. Our proposed cache decision policy makes popular contents located edge area of a network, which stabilizes popular cached contents. Moderate popular contents tend to be stored in core area, which induces in-network guided requests to encounter cached contents more frequently. Our performance evaluation results reveal that the combination of Breadcrumbs and our proposed cache decision policy improves cache hit performance compared to existing cache decision policies.

DOI： 10.1109/CQR.2017.8289446

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Institute of Electronics, Information and Communication, Engineers, IEICE  

In recent years, software-defined networking (SDN), which performs centralized network management with software, has attracted much attention. Although packets are transmitted based on flow entries in SDN switches, the number of flow entries that the SDN switches can handle is limited. To overcome this difficulty, this paper proposes a flow-based routing method that performs flexible routing control with a small number of flow entries. The proposed method provides mixed integer programming. It assigns common paths to flows that can be aggregated at intermediate switches, while considering the utilization of network links. Because it is difficult for mixed integer programming to compute largescale problems, the proposed method also provides a heuristic algorithm for them. Through numerical experiments, this paper shows that the proposed method efficiently reduces both the number of flow entries and the loads of congested links.

DOI： 10.1587/transcom.2017ITP0007

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Information Processing Society of Japan  

This paper first investigates how a network operates when multiple receivers download content simultaneously in content-centric networking (CCN) when the receivers’ downloading speeds differ. The results indicate that the performance of the download completion time of a faster user degrades excessively due to a decrease in the cache-hit rate in the router. Based on the investigation, this paper proposes a novel in-network caching method for simultaneous download from multiple receivers in CCNs. The proposed method keeps cached data packets in a router until slower receivers download the data, in order to prevent slower users from directly downloading data from the content provider. We conduct computer simulations and confirm the effectiveness of the proposed method. We show that the proposed method can improve the download completion time performance in the situation where multiple receivers download content at different speeds in CCN.

DOI： 10.2197/ipsjjip.25.164

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

This paper proposes a data center traffic engineering scheme with Markov approximation. Markov approximation is a distributed optimization framework. It optimizes networks by independent behaviors of users that construct a time-reversible continuous-time Markov chain based on minimum necessary information in the networks. The proposed scheme aims at minimizing the maximum link utilization in data center networks by means of Markov approximation. The proposed scheme provides two strategies with different search space. Through simulation experiments, we show that the proposed scheme efficiently reduces the maximum link utilization under not only static situations but also dynamic situations where traffic demands dynamically change in data center networks.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In recent years, software-defined networking (SDN), which performs centralized network management with software, has attracted much attention. In SDN, the data plane is separated from the control plane. Network administrators can dynamically change the setting of the data plane and control routing on the control plane through a control protocol such as OpenFlow. Although packets are transmitted based on flow entries in the data plane, the number of flow entries that data plane can have is limited. It is difficult to perform flexible routing control with a small number of flow entries. To overcome this difficulty, this paper proposes a routing method that reduces the number of flow entries, while reducing the maximum link utilization. The proposed method allocates common paths to flows that can be aggregated, considering the utilization of the links. Through numerical experiments, this paper shows the effectiveness of the proposed method.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Communication infrastructures under the influence of the disaster strike, e.g., earthquake, will be partitioned due to the significant damage of network components such as base stations. The communication model of the Internet bases on a location-oriented ID, i.e., IP address, and depends on the DNS (Domain Name System) for name resolution. Therefore such damage remarkably deprives the reachability to the information. To achieve robustness of information retrieval in disaster situation, we try to apply CCN/NDN (Content-Centric Networking/Named-Data Networking) to information networks fragmented by the disaster strike. However, existing retransmission control in CCN is not suitable for the fragmented networks with intermittent links due to the timer-based end-to-end behavior. Also, the intermittent links cause a problem for cache behavior. In order to resolve these technical issues, we propose a new packet forwarding scheme with the dynamic routing protocol which resolves retransmission control problem and cache control scheme suitable for the fragmented networks. Our simulation results reveal that the proposed caching scheme can stably store popular contents into cache storages of routers and improve cache hit ratio. And they also reveal that our proposed packet forwarding method significantly improves traffic load, energy consumption and content retrieval delay in fragmented networks.

DOI： 10.1587/transcom.2016CNP0003

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Quantized congestion notification (QCN), discussed in IEEE 802.1Qau, is one of the most promising Layer 2 congestion control methods for data center networks. Because data center networks have fundamentally symmetric structures and links are designed to have high link utilization, data center flows often pass through multiple bottleneck links. QCN reduces its transmission rate in a probabilistic manner with each congestion notification feedback reception, which might cause excessive regulation of the transmission rate in a multiple-bottleneck case because each bottleneck causes congestion feedbacks. We have already proposed QCN with bottleneck selection (QCN/BS) for multicast communications in data center networks. Although QCN/BS was originally proposed for multicast communications, it can also be applied to unicast communications with multiple bottleneck points. QCN/BS calculates the congestion level for each switch based on feedback from the switch and adjusts its transmission rate to the worst congestion level. In this paper, we preliminarily evaluate QCN/BS in unicast communications with multiple tandem bottleneck points. Our preliminary evaluation reveals that QCN/BS can resolve the excessive rate regulation problem of QCN but has new fairness problems for long-hop flows. To resolve this, we propose a new algorithm that integrates QCN/BS and our already proposed Adaptive BC_LIMIT. In Adaptive BC_LIMIT, the opportunities for rate increase are almost the same for all flows even if their transmission rates differ, enabling an accelerated convergence of fair rate allocation among flows sharing a bottleneck link. The integrated algorithm is the first congestion control mechanism that takes into account unicast flows passing through multiple tandem bottleneck points based on QCN. Furthermore, it does not require any modifications of switches used in QCN. Our simulation results show that our proposed integration of QCN/BS and Adaptive BC_LIMIT significantly mitigates the fairness problem for unicast communications with multiple bottleneck points in data center networks.

DOI： 10.1587/transcom.2015EBP3404

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Content oriented network is expected to be one of the most promising approaches for resolving design concept difference between content oriented network services and location oriented architecture of current network infrastructure. There have been proposed several content oriented network architectures, but research efforts for content oriented networks have just started and technical issues to be resolved are still remained. Because of content oriented feature, content data transmitted in a network can be reused by content requests from other users. Pervasive cache is one of the most important benefits brought by the content oriented network architecture, which forms interconnected caching networks. Caching network is the hottest research area and lots of research activities have been published. This paper surveys recent research activities for caching networks in content oriented networks, with focusing on important factors which affect caching network performance, i.e. content request routing, caching decision, and replacement policy of cache. And this paper also discusses future direction of caching network researches.

DOI： 10.1587/transcom.2015AMI0001

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In recent years, much work has been devoted to developing protocols and architectures for supporting the growing trend of data-oriented services. One drawback of many of these proposals is the need to upgrade or replace all the routers in order for the new systems to work. Among the few systems that allow for gradual deployment is the recently-proposed Breadcrumbs technique for distributed coordination among caches in a cache network. Breadcrumbs uses information collected locally at each cache during past downloads to support in-network guiding of current requests to desired content. Specifically, during content download a series of short-term pointers, called breadcrumbs, is set up along the download path. Future requests for this content are initially routed towards the server which holds (a copy of) this content. However, if this route leads the request to a Breadcrumbs-supporting router, this router re-directs the request in the direction of the latest downloaded, using the aforementioned pointers. Thus, content requests are initially forwarded by a location ID (e.g., IP address), but encountering a breadcrumb entry can cause a shift over to content-based routing. This property enables the Breadcrumbs system to be deployed gradually, since it only enhances the existing location-based routing mechanism (i.e. IP-based routing). In this paper we evaluate the performance of a network where Breadcrumbs is only partially deployed. Our simulation results show Breadcrumbs performs poorly when sparsely deployed. However, if an overlay of Breadcrumbs-supporting routers is set-up, system performance is greatly improved. We believe that the reduced load on servers achieved with even a limited deployment of Breadcrumbs-supporting routers, combined with the flexibility of being able to deploy the system gradually, should motivate further investigation and eventual deployment of Breadcrumbs. In the paper, we also evaluate more coarse level than router level, i.e. ISP-level Breadcrumbs deployment issues. Our evaluation results show that Higher-layer first deployment approach obtains great improvement caused by Breadcrumbs redirections because of traffic aggregation in higher layer ISP.

DOI： 10.1587/transcom.2014EBP3471

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：ASSOC COMPUTING MACHINERY  

Content Centric Networking (CCN) is one of the most promising content-oriented network architectures. In CCN, forwarding information base (FIB) is allowed to have multiple entries for a same content name prefix, which means CCN potentially supports multi-source download. When a content is obtained from multiple sources, the technical knowledge obtained for congestion control in the current Internet cannot be simply applied. This is because in the current Internet, FIB is restricted to have only one entry for each IP address prefix, which causes quite different path feature from CCN. This paper proposes a new congestion control for CCN with multi-source content retrieval. The proposed congestion control is composed of end-to-end window flow control and router assisted Interest forwarding control and enables transmission rate regulation only on a congested branch.

DOI： 10.1145/2984356.2985235

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In content oriented networks (CON), routers in a network are generally equipped with local cache memories and store incoming contents temporally. Efficient utilization of total cache storage in networks is one of the most important technical issues in CON, which brings reduction of content server load, content download latency and network traffic. Performance of networked cache is reported to strongly depend on combination of caching decision and content request routing. In this paper, we evaluate several combinations of these two strategies. Especially for routing, we take up off-path cache routing, Breadcrumbs, as one of evaluated content request routings. Our performance evaluation results show that off-path cache routing, Breadcrumbs, obtains poor performance with caching decisions which has good performance with shortest path routing (SPR), and obtains good performance with TERC (Transparent En-Route Cache) which is well-known to have poor performance with widely used SPR.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In-network guidance for off-path caching, called Breadcrumbs, has been proposed for cache networks. In Breadcrumbs, during content download, a router holds a pointer, breadcrumb, which denotes the latest download direction. When a content request occasionally encounters a breadcrumb along its default-path to the repository, location-based routing is switched to hop-by-hop breadcrumb-based routing and it is forwarded to off-path cache. In our previous work, we evaluated Breadcrumbs in fixed wireless multi-hop networks and showed that total network throughput is significantly improved. In this paper, we focus on mobile wireless multi-hop networks where Breadcrumbs trail might be fragmented due to node mobility. To resolve this technical problem in mobile environment, we propose a new in-network guidance method, overhearing-aided Breadcrumbs. In overhearing-aided Breadcrumbs, a router which overhears content download by other nodes makes one-hop breadcrumb. Our evaluation results show that proposed overhearing-aided Breadcrumbs outperforms conventional Breadcrumbs in mobile wireless multi-hop networks.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this paper, we first investigate how a network works when multiple receivers download content simultaneously in content-centric networking (CCN). We are especially interested in the case that the receivers' downloading speeds differ. From our investigation, we show that the download completion time of a faster user degrades excessively due to the problem that there being different downloading speeds decreases the cache-hit rate. To solve this problem, we propose a novel cache management method for simultaneous downloading from multiple receivers for CCN. The concept of the proposed method is to keep cached data packets in a router until they are transferred to the receiver. The proposed method increases the cache-hit rate for a slower receiver, and prevents a slower user from directly downloading data from the content provider. Through computer simulations, we confirm that the proposed method can improve the download completion time performance in the situation that multiple receivers download content at different speeds in CCN.

DOI： 10.1109/WAINA.2016.133

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Large-scale content transfer, especially video transfer, is now a dominant traffic component in the Internet. Originally, content transfer had a content-oriented feature, i.e., "Users do not care where content is retrieved. Users only take care of what content they obtain." Conventional traffic engineering (TE) aims to obtain optimal routes for traffic between ingress and egress router pairs, i.e., TE has focused on a location-oriented approach that takes care of where to connect. With increased demand for content-oriented features for content traffic, TE needs to focus on content-oriented routing design. In this study, we therefore propose a novel approach to content-oriented TE, called content aware routing (CAR). In CAR, routes are designed for content and egress router pairs, i.e., content traffic toward a receiver-side router. Content demand can be flexibly distributed to multiple servers (i.e., repositories) providing the same content, meaning that content can be obtained from anywhere. CAR solves the optimization problem of minimizing maximum link utilization. If there are multiple optimal solutions, CAR selects a solution in which resource usage is minimized. Using numerical examples formulated by the linear programming problem, we evaluated CAR by comparing it with combinations of conventional content delivery networks and TE, i.e., location-oriented designs. Our numerical results showed that CAR improved maximum link utilization by up to 15%, with only a 5% increase of network resource usage.

DOI： 10.1587/transcom.E98.B.575

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Data center network is composed of high-speed Ethernet extended in a limited area of a data center building, so its RTT is extremely small of mu sec order. In order to regulate data center network delay large part of which is queuing delay, QCN is proposed for layer 2 congestion control in IEEE 802.1Qau. QCN controls transmission rate of the sender by congestion feedback from a congested switch. QCN adopts probabilistic feedback transmission to reduce the control overhead. When the number of flows through a bottleneck link increases, some flows might receive no feedback even in congestion phase due to probabilistic feedback transmission. In this situation, queue length might be significantly fluctuated. In this paper, we propose a new delay-based congestion detection and control method. Our proposed delay-based congestion control is cooperated with the conventional QCN so as to detect and react congestion not detected by QCN.

DOI： 10.1587/transcom.E98.B.585

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：National Institute of Information and Communications Technology  

Content distribution will be one of main applications in future networks. To realize the concept of Space Decoupling, which is supported by the fact that users have only to acquire desired contents irrespective of where they are located, we developed effective technologies to retrieve and transfer cached contents efficiently by exploiting in-network guidance functions. In this paper, we introduce the main results of our research project in terms of both content retrieval and content transfer.

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In content oriented application, such as P2P, a user does not care about where content is obtained and a content file can be downloaded from anywhere it is obtained. In some P2P systems, e.g. BitTorrent, a content file is divided into small parts, chunks, and each chunk is downloaded from anywhere. In this many-to-one communication style, one TCP session is set up for each pair of a sender and a receiver. If these sessions go through the same bottleneck link, many-to-one communication might obtain unfairly large throughput. In this paper, we propose a new receiver-driven congestion control for this many-to-one communications. Our proposed congestion control detects bottleneck-sharing flows and clusters them. Window coupling technique is applied for these clustered flows, which enables these flows to obtain fair aggregated throughput. Our simulation results show that our proposed receiver-driven congestion control fairly shares a bottleneck link with regular TCP.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Network traffic for sharing contents is significantly increasing. The cache network is a desirable architecture to reduce traffic and to improve reliability of contents retrieval. "Breadcrumbs" is one of the promising techniques to find cached contents in a distributed manner. Thanks to Breadcrumbs, users can retrieve a content without managing where the cache exists. This demo shows a contents sharing application among mobile users in the Breadcrumbs-enabled cache network.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Communication infrastructures under the influence of the disaster strike e.g., earthquake, will be partitioned due to the damage of components such as base stations. The communication model of the Internet bases on a location-oriented ID, i.e., IP address, and depends on the DNS (Domain Name System) for name resolution. Therefore such damage remarkably deprives the reachability to the information. To achieve robustness of information retrieval in disaster situation, we try to apply CCN (Content-Centric Networking) to fragmented networks. Since CCN does not require name resolution, it can work without the global system such as DNS. However, existing retransmission control in CCN is not suitable for the fragmented networks with intermittent links due to the timer-based end-to-end scheme. Though the requirement to save energy and bandwidth are critical in disaster case, overhead caused by redundant retransmissions might waste bandwidth and energy. Accordingly, we propose the energy efficient retransmission scheme with the dynamic routing protocol suitable for fragmented networks. With the proposed method, messages are forwarded hop-by-hop with recognizing whether the state of links is connected or not. Simulation results reveal that the proposed method can reduce traffic load, energy consumption and delay of contents retrieval.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Because of the popularity of rich content, such as video files, the amount of traffic on the Internet continues to grow every year. Not only is the overall traffic increasing, but also the temporal fluctuations in traffic are increasing, and differences in the amounts of traffic between peak and off-peak periods are becoming very large. Consequently, efficient use of link bandwidth is becoming more challenging. In this paper, we propose a new system for content distribution: storage aware routing (SAR). With SAR, routers having large storage capacities can exploit those links that are underutilized. Our performance evaluations show that SAR can smooth the fluctuations in link utilization.

DOI： 10.1587/transcom.E97.B.2641

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In data center networks, group communication is currently playing an important role and multicast communications is an effective way to support group communication for large numbers of virtual machines. Layer-2 congestion control named QCN (Quantized Congestion Notification) has been proposed to realize the high reliability required by LAN/SAN integration in data center networking. Our preliminary evaluation in this paper shows that a multicast flow suffers lower throughput than unicast flows when conventional QCN is applied in a naive manner. This is because a sending device receives congestion feedback from multiple locations on a multicast tree and decreases transmission rate accordingly. To counter this throughput degradation of multicast flows, we propose a new Layer 2 congestion control algorithm in multicast environment, Quantized Congestion Notification with Bottleneck Selection (QCN/BS). In QCN/BS, the switch in the worst congestion level is selected and the transmission rate of the sending device is calculated exclusively according to feedback from the selected switch. Simulation results show that when conventional QCN is used, a multicast flow experiences lower and more severely unfair throughput than a unicast flow. The proposed QCN/BS resolves this problem.

DOI： 10.1587/transcom.E97.B.1121

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In wireless multi-hop networks, content servers are generally located outside a wireless multi-hop network and a user accesses these servers through a gateway node. So, content traffic has a tendency to be concentrated at a gateway node, which might cause throughput degradation in a whole wireless multi-hop network. Caching network is one promising way to resolve this technical problem. However, caching network has a limitation of cache availability on a default-path. For wired networks, Breadcrumbs has been proposed as in-network guide for cached contents. In this paper, we evaluate Breadcrumbs in wireless multi-hop networks. Our simulation results show that Breadcrumbs improves total throughput performance of wireless multi-hop networks. And also they surprisingly show that not only popular content throughput but also unpopular content throughput is improved.

Web of Science

researchmap

Language：English   Publisher：The Institute of Electronics, Information and Communication Engineers  

ID/Locator separation architecture is proposed in order to reduce routing table size in the current Internet. In this architecture, an end-host can be identified by unique ID which is independent of its network protocol. Network protocol independency of ID provides possibility of communication with end hosts operating different network-layer protocol. This inter-layer 3 networking brings several benefits in addition to routing table size improvement, e.g. improvement of shortest path and robustness. In our previous paper, performance of inter-layer 3 networking from the viewpoint of shortest path improvement has been evaluated. In this paper, we focus on improvement of robustness brought by inter-layer 3 networking in the case of node failure. Node failure generally suffers serious degradation of connectivity because all links connected to a node are failed. Our simulation results show that significant improvement of robustness can be obtained only with small number of vertical links going through multiple network planes.

DOI： 10.1587/comex.2.372

researchmap

researchmap

Language：English   Publisher：The Institute of Electronics, Information and Communication Engineers  

Network topology significantly affects network cost, path length, link load distribution, and reliability, so we need to consider multiple criteria with different units simultaneously when designing a network′s topology. The analytic hierarchy process (AHP) is a technique of balancing multiple criteria in order to reach a rational decision. Using AHP, we can reflect the relative importance of each criterion on the evaluation result; therefore, we have applied it to network topology evaluation in past research. When evaluating network topologies using AHP, we need to construct the set of topology candidates prior to the evaluation. However, the time required to construct this set greatly increases as the network size grows. In this paper, we propose applying a binary partition approach for constructing a topology candidate set with dramatically reduced calculation time. To reduce the calculation time, we introduce an upper limit for the total link length. Although the results of AHP are affected by introducing the upper limit of the total link length, we show that desirable topologies are still selected in AHP.

DOI： 10.1587/transcom.E96.B.163

CiNii Books

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In large-scale data centers, two types of network are implemented: local area networks (LANs) and storage area networks (SANs). To achieve simple network management, integration of these two networks by Ethernet technology is of great interest. A SAN requires a significantly low frame loss rate. To integrate LANs and SANs, a multi-hop Ethernet configuration is generally used, and congestion may occur in traffic hot spots. Therefore, layer-2 congestion control that prevents frame loss in multi-hop Ethernet, Quantized Congestion Notification (QCN), is now discussed in IEEE 802.1Qau. In this paper, we evaluate QCN's throughput performance and reveal a technical problem with fairness among active flows. We also propose Adaptive BC_LIMIT for QCN where BC_LIMIT is adaptively decided according to current transmission rate of flows. Simulation results show that our proposed method significantly improves fairness among QCN flows.

DOI： 10.1587/transcom.E96.B.99

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In recent years, much work has been devoted to developing protocols and architectures for supporting the growing trend of data-oriented services. One drawback of many of these proposals is the need to upgrade or replace all the routers in order for the new systems to work. Among the few systems that allow for gradual deployment is the recently-proposed Breadcrumbs technique for distributed coordination among caches in a cache network. Breadcrumbs uses information collected locally at each cache during past downloads to support in-network guiding of current requests to desired content. Specifically, during content download a series of short-term pointers, called breadcrumbs, is set up along the download path. Future requests for this content are initially routed towards the server which holds (a copy of) this content. However, if this route leads the request to a Breadcrumbs-supporting router, this router re-directs the request in the direction of the latest downloaded, using the aforementioned pointers. Thus, content requests are initially forwarded by a location ID (e. g., IP address), but encountering a breadcrumb entry can cause a shift over to content-based routing. This property enables the Breadcrumbs system to be deployed gradually, since it only enhances the existing location-based routing mechanism (i.e. IP-based routing).
In this paper we evaluate the performance of a network where Breadcrumbs is only partially deployed. Our simulation results show Breadcrumbs performs poorly when sparsely deployed. However, if an overlay of Breadcrumbs-supporting routers is set-up, system performance is greatly improved. We believe that the reduced load on servers achieved with even a limited deployment of Breadcrumbs-supporting routers, combined with the flexibility of being able to deploy the system gradually, should motivate further investigation and eventual deployment of Breadcrumbs.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In research community of content distribution, a new communication paradigm of rendezvous-based abstraction which easily enables location-free content-oriented services, attracts great attention. ID/Locator separation architecture is originally proposed for resolving increase of routing table size in the current Internet but it has possibility of supporting this abstraction because host ID is clearly separated from its location. This feature of ID/Locator separation means an end host can be identified by ID independent of its network layer protocol. So, ID/Locator separation architecture enables communication with end host(s) operating different network-layer protocol, which might increase candidate paths between host pairs and improve content distribution path. In this paper, we evaluate this improvement of shortest path brought by inter-layer 3 networking. In inter-layer 3 networking, a shared node connecting different network layer plane plays an important role. We evaluate shortest path improvement with various shared node locations and show that strategic assignment of shared nodes brings large improvement. When multiple layer 3 networks are available for users, shortest path might be improved even only with multi-homing (without inter-layer 3 networking). We also evaluate shortest path improvement brought by multi-homing and inter-layer 3 networking for incremental deployment scenario of multi-homing. Our simulation results show that inter-layer 3 networking brings great improvement even with small number of users deploying multi-homing while only multi-homing itself brings small improvement.

DOI： 10.1587/transcom.E94.B.2741

Web of Science

researchmap

J-GLOBAL

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In ad hoc wireless networks, end-to-end TCP is well-known that it can obtain very low throughput with increase of the number of hops. One promising way to resolve this technical problem of TCP throughput degradation is proxy-based TCP. In proxy-based TCP, an end-to-end TCP session is divided by (an) intermediate proxy host(s), which leads to reduction of hop-count of each divided session and improvement of TCP throughput. However, we show that proxy-based TCP surprisingly does not bring performance improvement and obtain lower throughput than conventional end-to-end TCP in a realistic situation of limited buffer space in proxy host(s). The reason for this degradation is interruption of segment transmission caused by wireless channel capture around the proxy host. In this paper, for resolving this problem, we propose intentional window How control which prevents wireless channel capture around the proxy host. In our proposed intentional window flow control method, the proxy host and the destination host return advertised window size which is intentionally set to small value almost independently from its vacant buffer space. Performance evaluation results show that our proposed intentional flow control with small advertised window size prevents wireless channel capture around the proxy host and significantly improves proxy-based TCP performance.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In wireless multi-hop networks, when an end host would like to communicate with external wired hosts, data packets are to be transmitted at first to a gateway node which is connected to both a wireless multi-hop network and a wired network. When there are multiple candidate gateways to be connected, a wireless host should select one gateway as its own default gateway. One possible and simple way is minimum hop gateway selection policy. This minimum hop gateway selection may cause performance degradation in the case of imbalance of traffic distribution. In this paper, we propose a new gateway selection method where an end host selects the default gateway from the viewpoint of gateway load balancing. Wireless communication channel around the gateway is very important resource because all the external traffic goes through the gateway. So, gateway load in our proposed method takes account of not only traffic intensity at a gateway but also interference of wireless channel around a gateway. Our simulation results show that our proposed method brings improvement of gateway throughput performance.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

ALM (Application Level Multicast) is one of the promising ways for resolving multicast incentive problem of non-multicast hosts not implementing multicast routing protocol. ALM protocol is implemented in application layer, which means it is easier to be altered by end users than lower layer protocols. Malicious users would like to get higher position in ALM tree because it can obtain higher throughput and lower delay. They also would not like other hosts to be connected because of forwarding burden will bring them wireless throughput degradation. This paper evaluates performance improvement perceived by a malicious user and shows that surprisingly it can obtain performance improvement only with almost 50% probability. We also investigate the reason why this performance effect and show that link sharing with other ALM hosts in long hops is one of the reasons of performance degradation of malicious users. ©2009 IEEE.

DOI： 10.1109/APCC.2009.5375478

Scopus

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)  

Multicast communication is an e.cient packet dissemination method in ad hoc network. However, in ad hoc multicast communication, packet collisions due to the hidden terminal problem happen frequently because each host does not use the RTS/CTS frames that has been used in conventional unicast communication. So, wireless channel is not reserved for any multicast packet transmissions and hidden terminal problem degrades multicast communication performance. One promising way for improving hidden terminal problem is directional antenna. Because interference can be decreased by directional antenna, the hiding terminal problem can be improved. In this paper, we evaluate basic performance of multicast communication with directional antenna in ad hoc networks. Performance evaluation by computer simulation shows that throughput performance can be improved by using directional antenna because the radio wave interference decreases and the hidden terminal problem that is brought by some independent multicast sessions can be controlled. ©2009 IEEE.

DOI： 10.1109/APCC.2009.5375481

Scopus

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Application-level multicast has drawn a lot of attention as an alternative to IP multicast. In application-level multicast, multicast related features, such as group membership management, packet replication and packet forwarding are implemented at end-hosts instead of routers. The host perceived transmission quality and multicast forwarding responsibility depend on its position in the multicast distribution tree. This nature of application-level multicast motivates selfish members to alter their position by unrightful means to maximize their private benefits. Uncooperative behaviors of these selfish members, i.e. cheating, increase unfairness between selfish members and faithful members. In the context of bulk data distribution, this unfairness between members significantly impacts the receiver throughput. In this paper, to alleviate the negative impact of cheating members, we propose a new tree building protocol which builds dual multicast trees. Our proposed protocol constructs a shortest-widest path tree as the 1st tree. The members having lower position in the 1st tree are located at higher position in the 2nd tree in exchange for their Unfairness. To investigate performance of our proposed protocol, it is compared with the existing application-level multicast protocol. Our simulation results show that our protocol outperforms the existing protocol from the view point of throughput and resource utilization against member cheating.

DOI： 10.1093/ietcom/e91-b.12.3872

Web of Science

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In ad hoc networks, a TCP session can obtain very low throughput with increase of the number of hops. One promising way to resolve this technical problem of TCP throughput degradation is proxy-based TCP. In proxy-based TCP, an end-to- end TCP session is divided by (an) intermediate proxy host(s), which leads to reduction of RTT of each divided session and improvement of TCP throughput. We evaluate proxy-based TCP in ad hoc networks with a realistic assumption of finite buffer in proxy hosts. Our simulation results show that proxy-based TCP surprisingly does not bring performance improvement and obtain lower throughput than conventional end-to-end TCP. In the paper, we show that wireless channel capture around the proxy host is the reason for this degradation. And we propose adaptive rate control method and intentional flow control method at the proxy host which improves throughput performance of proxy-based TCP. Performance evaluation results show that proxy-based TCP with our proposed methods outperforms conventional end-to-end TCP.

DOI： 10.1109/GLOCOM.2008.ECP.163

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In Multicast is an effective way of dissemination of the same information to potentially large number of users. In IP multicast, a multicast IP address is used for identifying each multicast session. When large number of various contents should be disseminated, e.g. software distribution to various types of information home appliances, lots of multicast addresses are necessary. Source Port Specific Multicast (SPSM) is an effective way of saving IP multicast addresses. In SPSM, both of a source port of transport layer and an IP address in network layer is used for identification of multicast session. When SPSM routers are partially deployed, i.e. SPSM routers and non-SPSM routers (IP multicast router) co-exist in a network, unnecessary traffic may be generated because non-SPSM routers cannot identify multicast sessions having the same multicast address. In this paper, we analyze this unnecessary traffic volume with various deployment scenes of SPSM routers.

Web of Science

researchmap

Language：English   Publisher：Information and Media Technologies Editorial Board  

Ad hoc network which requires no infrastructure equipment such as access points is paid great attention in recent years. In ad hoc network, each host controls its wireless access in a distributed fashion. Generally, carrier sensing is used for detecting channel availability. By using RTS and CTS control frames, MAC sub-layer predicts the channel use and resolves hidden-terminal problem. Broadcast nature of RTS and CTS control frames leads to inefficient spatial reuse. One promising solution for this inefficient spatial reuse is usage of directional antenna. In ad hoc networks, heterogeneous network configuration is general, which means each host is equipped with different network facilities. For antennas, it will be general situation that not all hosts are equipped with directional antenna. This paper evaluates throughput performance of the ad hoc network in this realistic situation and shows how much performance improvement deployment of directional antenna will bring to the network.

DOI： 10.11185/imt.2.907

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In this paper, we discuss TCP performance in a wireless overlay network where wireless LANs and cellular networks are integrated. In the overlay network, vertical handover, where a mobile node changes its access link during a session, is one of the most important technologies. When a vertical handover occurs, throughput performance of a TCP flow is degraded due to not only packet losses during the handover, but drastic change of its bandwidth-delay product. In this paper, we propose an ACK-pacing mechanism for TCP congestion control to improve the performance degradation. The proposed system is receiver-driven, so no modification is required to the mechanism of TCP sender. In the proposed system, a TCP receiver adjusts a transmission rate of ACKs according to the relationship between bandwidth-delay products before and after a handover. Since the ACK-clocking mechanism of TCP adjusts the transmission rate of TCP segments, the TCP receiver can seamlessly adjust its congestion window size to the new bandwidth-delay product. Computer simulation results show that the proposed system can improve the TCP performance during the vertical handover.

DOI： 10.1093/ietcom/e90-b.4.885

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：SPRINGER-VERLAG BERLIN  

Recently the content distribution networks (CDNs) are highlighted as the new network paradigm which can improve latency for Web access. In CDNs, the content location strategy and request routing techniques are important technical issues. Both of them should be used in an integrated manner in general, but CDN performance applying both these technologies has not been evaluated in detail. In this paper, we investigate effect of integration of these techniques. For request routing, we focus on a request routing technique applied active network technology, Active Anycast, which improves both network delay and server processing delay. For content distribution technology, we propose a new strategy, Popularity-Probability, whose aim corresponds with that of Active Anycast. Performance evaluation results show that integration of Active Anycast and Popularity-Probability provides robust CDNs.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：SPRINGER-VERLAG BERLIN  

Recently the content distribution networks (CDNs) are highlighted as the new network paradigm which can improve latency for Web access. In CDNs, the content location strategy and request routing techniques are important technical issues. Both of them should be used in an integrated manner in general, but CDN performance applying both these technologies has not been evaluated in detail. In this paper, we investigate effect of integration of these techniques. For request routing, we focus on a request routing technique applied active network technology, Active Anycast, which improves both network delay and server processing delay. For content distribution technology, we propose a new strategy, Popularity-Probability, whose aim corresponds with that of Active Anycast. Performance evaluation results show that integration of Active Anycast and Popularity-Probability provides robust CDNs.

Web of Science

researchmap

Language：English   Publisher：Information and Media Technologies Editorial Board  

Self-similar traffic patterns have been observed in many measurements of Internet traffic. Self-similarity is very detrimental to the performance of packet networks and recent research has focused on understanding and reducing its amount in Internet traffic. TCP Reno has been identified as being one of the primary sources of self-similarity. We explore the potential of another version of TCP in this paper to reduce the degree of self-similarity in aggregated TCP traffic. We decompose both TCP Reno and TCP Vegas to demonstrate and explain their underlying mechanisms, and separately measure what effects congestion-avoidance and timeouts/exponential backoff mechanisms have on the self-similarity in aggregated TCP flows. We reveal how TCP Vegas reduces the degree of self-similarity and eventually completely eliminates it from aggregated TCP flows at low levels of packet loss. However, at high levels of packet loss we show that TCP Vegas is detrimental, because it increases the degree of aggregated TCP-flow self-similarity.

DOI： 10.11185/imt.2.347

researchmap

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：SPRINGER-VERLAG BERLIN  

IP multicast is an effective technology to distribute identical data simultaneously to multiple users. However, for technical and administrative reasons, IP multicast has not been globally deployed on the Internet. Another approach to multicast is application-level multicast (ALM). In ALM, multicast related features, such as group membership management, multicast routing and packet replication, are implemented at end-hosts instead of routers. Multicast delivery tree is constructed in the application layer, so all nodes in this tree are end-hosts. Packet transmission between end-hosts uses conventional IP unicast service. Therefore, ALM is a promising alternative to IP multicast. However, application-level multicast relying on end-hosts is more fragile than IP multicast relying on routers. Especially, when a mobile host forwards packets to downstream hosts, a handover causes performance degradations on downstream hosts. In this paper, to alleviate the impact of a handover, we propose a new tree building protocol which locates mobile hosts on leaves of multicast tree. A handover of the mobile host on a leaf does not affect other end-hosts. To investigate performance of our protocol, it is compared with existing application-level multicast protocols. Our simulation results show that our protocol outperforms existing protocols from the viewpoints of loss probability, throughput and delay performance.

Web of Science

researchmap

Language：English   Publisher：Information Processing Society of Japan  

There have been no studies evaluating the dominant factor responsible for generating self-similar network traffic, although many researchers have discussed the causes of self-similarity. In this paper, we have isolated and compared the effects of the application, transport and network layers on self-similarity. We first focus on the interaction between the transport and network layers only. With a simple computer simulation scenario we show that in realistic bottleneck scenarios with only long greedy TCP flows present, the TCP flows fully utilize the bottleneck link, which make the aggregated TCP flow short-range dependent while each flow that share the bottleneck link itself is long range dependent. We also show that in special situations, when the TCP flows become synchronized, the bottleneck link may become underutilized giving space to long-range dependence to surface. We show the connection between the network layer parameters necessary for synchronization to occur, and verify our results with simulation. To examine the effect of the application layer, we introduce web traffic besides the long greedy flows into the bottleneck link. We show that link utilization is again a key factor determining the self-similar properties of the aggregated flow, but has much less impact on the self-similar properties of the aggregated web sessions and long greedy flows. Finally, we point out the most influential effects and the conditions when they dominate the self-similar properties of aggregated TCP flows.

DOI： 10.2197/ipsjdc.1.576

researchmap

科研費基盤研究 20040401-20060331

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In multicast congestion control, the receiver of the worst congestion level is selected as the representative and transmission rate of the sender is adjusted to TCP throughput of the representative. This approach has high scalability and TCP friendliness. However, when this approach is applied in wireless communications, wireless-caused packet loss will cause to frequent change of the representative. This is because degradation of wireless channel quality causes bursty packet loss at a corresponding receiver. Fading, one of main reasons of wireless channel degradation, is expected to be recovered after short time period, which leads to frequent change of the representative. This frequent change of representative makes the sender adjust its transmission rate to the tentative worst receiver, which brings severe performance degradation to wireless multicast. We call this technical problem, the wireless-caused representative selection fluctuation problem. Wireless-caused representative selection fluctuation problem is one of scalability problems in the wireless multicast, because this problem remarkably happens for large scale multicast. We propose two possible solutions for this problem, an end-to-end approach and a network support approach. Performance evaluation in various situation show that an end-to-end approach is sensitive for its inferring error but a network support approach shows good performance improvement.

DOI： 10.1093/ietcom/e88-b.7.2819

Web of Science

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In the mobile Internet, a handover brings significant performance degradation of TCP due to bursty packet losses during handover processing. In this paper, we propose a new bandwidth control for improving the TCP performance. In the proposed system, when a mobile node changes its accessing base station, an intermediate router suppresses an available bandwidth to the corresponding TCP flow. Because suppressing the bandwidth results in reducing mis-forwarded packets to the old base station, the bursty packet losses can be avoided. In the hierarchical mobile network structure, which is recently developed in order to realize micromobility protocol, all packets transferred to mobile nodes are converged to several gateways such as mobility anchor points (MAP) in hierarchical Mobile IPv6 (HMIPv6). Therefore, the proposed system is suited to the hierarchical structure because it can be easily implemented at such gateways. Computer simulation results show that the proposed system can improve the TCP performance degradation especially in a situation where handovers frequently occur.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In content distribution networks(CDNs), the request routing which directs user requests to an adequate server from the viewpoint of improvement of latency for obtaining contents is one of the most important technical issues. In the request routing, network support technology enables a router to select an adequate server by using information of server load and network delay. In this system, a network support router selects a server based on information between router and server, so the placement of network support router is important to improve performance of request routing. In this paper, we investigate an efficient placement method of network support router making use of statistical characteristics of Internet topology.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Application-level multicast (ALM) is a feasible alternative to IP multicast. In ALM, multicast related features, such as group membership management, multicast routing and packet replication, are implemented at end-hosts instead of routers. A multicast distribution tree is constructed in the application layer, so all nodes in this tree are end-hosts. Packet transmission between end-hosts uses conventional IP unicast service. Therefore, all end-liosts can enjoy multicast communications without IP multicast service. However, ALM has a serious problem that the multicast distribution tree is intrinsically fragile and an end-host failure causes tree partitions. In this paper, to deal with this problem, we propose a new tree construction protocol which makes outdegrees of intermediate nodes be balanced. The degree-balanced distribution tree can reduce the average number of nodes decoupled by tree partitions. To investigate performance of our protocol, it is compared with an existing ALM protocol. Our simulation results show that our protocol outperforms the existing protocol from the viewpoints of robustness, loss probability and receiver-perceived delay.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this paper, we discuss TCP congestion control in the future heterogeneous mobile Internet where various access links such as a wireless LAN and a cellular network are integrated. In the heterogeneous network, vertical handover, which is a handover technique between different types of access links, is one of the most important technologies. In the heterogeneous network, since mobile terminals can simultaneously receive packets from several wireless interfaces during a handover processing, a seamless vertical handover for layer 2 and layer 3 can be realized and as a result, no packet loss occurs due to the vertical handover. However, the vertical handover significantly degrades throughput performance of TCP because it causes drastic change in a bandwidth delay product of each TCP flow. In this paper, we propose an ACK-pacing mechanism for TCP congestion control to realize a seamless layer 4 handover. The proposed system is receiver-driven, so no modification is required to the mechanism of TCP sender. In the proposed system, a TCP receiver adjusts a transmission rate of ACKs according to the relationship between delay-bandwidth products before and after a handover. Since the ACK-clocking mechanism adjusts the transmission rate of TCP, TCP receiver can seamlessly adjust its congestion window size to the new delay-bandwidth product by transmission rate control of ACK. Computer simulation results show that the proposed system can improve the TCP performance during the vertical handover.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：Institute of Electronics, Information and Communication, Engineers, IEICE  

Application-level multicast (ALM) is a feasible alternative to IP multicast. In ALM, multicast related features, such as group membership management, multicast routing and packet replication, are implemented at end-hosts instead of routers. A multicast distribution tree is constructed in the application layer, so all nodes in this tree are end-hosts. Packet transmission between end-hosts uses conventional IP unicast service. Therefore, all end-hosts can enjoy multicast communications without IP multicast service. However, ALM has a serious problem that the multi-cast distribution tree is intrinsically fragile and an end-host failure causes tree partitions. In this paper, to deal with this problem, we propose a new tree construction protocol which makes outdegrees of intermediate nodes be balanced. The degree-balanced distribution tree can reduce the average number of nodes decoupled by tree partitions. To investigate performance of our protocol, it is compared with an existing ALM protocol. Our simulation results show that our protocol outperforms the existing protocol from the viewpoints of robustness, loss probability and receiver-perceived delay. Copyright © 2005 The Institute of Electronics, Information and Communication Engineers.

DOI： 10.1093/ietcom/e88-b.12.4427

Scopus

researchmap

科研費基盤研究 20040401-2006-0331

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

The window flow control based end-to-end TCP congestion control may cause unfair resource allocation among multiple TCP connections with different RTTs (round trip times) at a bottleneck link. In this paper, in order to improve this unfairness, we propose the active ECN which is an ECN based active queue mechanism (AQM). A bottleneck router with the proposed mechanism marks TCP segments with a probability which depends on the RTT of each connection. By enabling the TCP senders to reduce their transmission rate when their packets are marked, the proposed mechanism can realize the same transmission rate among TCP connections with different RTTs. Further-more, the active ECN can directly mark ACKs from TCP receivers. while the conventional ECN marks TCP segments coming from the TCP senders. As a result, the queue length distribution at the bottleneck link gets stabilized, because the sender can quickly react to the marking according to variation of the queue length.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In wireless environment, TCP suffers from significant performance degradation due to bit errors on wireless link and handovers because it responds to all packet losses by invoking congestion control even though packet losses are not related to congestion. Several schemes have been proposed to improve the performance degradation due to each cause. They have been evaluated in a specific network environment where either bit errors or handover occurs, i.e. they do not occur at the same time. In this paper, we reveal the packet recovery mismatch problem in an environment where both of bit errors and handover can cause the performance degradation. We pick up one scenario that TCP traffic is transmitted in the situation that ARQ (Automatic Repeat reQuest) and packet forwarding are implemented together. They are proposed to reduce the influence of bit errors and handover respectively and are natural approaches from the viewpoint of protocol layering. Computer simulation shows that in that scenario both techniques cannot perform efficiently due to interaction of each other. We also propose two buffer control approaches to resolve the packet recovery mismatch problem in our scenario according to applicability of cross-layer operation between layer 2 and layer 3.

Web of Science

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Large parts of the Internet are still incapable of native multicast, and ubiquitous deployment of multicast will take a long time. There are two approaches to provide wide-area multicast service in today's Internet. One is tunneling approach and the other is application-level multicast approach. In this paper, we focus on application-level multicast approach and propose a new scheme which improves the performance penalties of application-level multicast by making use of network support. Because in application-level multicast, endhosts provide multicast functionality instead of routers, application-level multicast delivery tree is inherently less efficient than IP multicast tree. Therefore, in our scheme, the router on the application-level multicast delivery tree alters the tree based on network-level delivery path. We evaluate our scheme with simulation experiment. Our simulation results indicate that our scheme improves the performance of application-level multicast. Further we compare our scheme to the tunneling approach from the viewpoint of transmission performances. The results reveal applicable domains of both approaches.

Web of Science

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE COMPUTER SOC  

TCP traffic has been reported to have not only self-similarity but also a multi-fractal nature. The multi-fractal nature of traffic volume in general is well known to have a significant influence on queueing behavior in short time scales. In our previous study, we showed that the Retransmission Time Out (RTO) mechanism plays an important role in the multi-fractal nature of TCP traffic.
In this paper we investigate how to control the multifiractal nature of TCP traffic in a real network Here we focus on the Random Early Detection (RED) mechanism in order to reduce the occurrence of RTO. We evaluate the RED mechanism from the viewpoint of multi-fractal nature and show that the RED mechanism improves not only throughput and delay performance, but also the multifractal nature of TCP traffic.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：SPRINGER-VERLAG BERLIN  

In mobile Internet, a handover may result in significant degradation of transmission performance. Especially in a shared medium wireless network, handover traffic which moves into a new wireless access network competes with existing traffic for available bandwidth of shared medium wireless channel. This interaction between handover traffic and existing traffic causes significant performance degradation of both of traffic. In this paper, we propose a new concept of Transport Layer Graceful Degradation. We think handover traffic should increase its available bandwidth gradually and available bandwidth of existing traffic is to be decreased slowly to bandwidth which achieves fair share of shared medium with handover traffic. In the paper, we propose a new bandwidth control method for TCP traffic which achieves our proposed concept, transport layer graceful degradation. Performance evaluation results show that our proposed scheme can improve TCP throughput performance of both handover traffic and existing traffic.

Web of Science

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Multicast communications have been expected as an effective way to disseminate information to potentially large number of receivers. IP multicast is a well- known multicast protocol for the Internet. However, IP multicast has several technical problems to be resolved until it is widely deployed in the Internet. These includes service-model of multicast group, reliable transport protocol, congestion control and security. A lot of researches trying to resolve these technical problems make multicast communications a hot research area in these couple of decades. This paper overviews the present style of IP multicast and clearlify technical issues of the present multicast communications. The paper also surveys important approaches to these problems and discuss about future directions of multicast communications.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In content distribution networks (CDNs), the content routing which directs user requests to an adequate server from the viewpoint of improvement of latency for obtaining contents is one of the most important technical issues. Several information, e.g. server load or network delay, can be used for content routing. Network support, e.g. active network, enables a router to select an adequate server by using these information. In the paper, we investigate a server selection policy of a network support approach from the viewpoint of which information to be used for effective server selection. We propose a server selection policy using RTT information measured at a router. Simulation results show that our proposed server selection policy in content routing selects a good server under both conditions where server latency and network delay is a dominant element of user response time. Furthermore, we also investigate about location of routers with network support bringing good performance for our proposed scheme.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

Multicast transmission, which can send the same information simultaneously to multiple users, is a key technology in content delivery networks. In this paper, we discuss a new multicast architecture with network coding proposed by Li et al., which breaks limitation of existing IP multicast in terms of network resource utilization. Network coding based multicast can achieve the max-flow, which is the theoretical upper bound of network resource utilization. However, the max-flow transmission is not always effective and may not be robust against congestion because it maximally uses link capacity of multicast distribution tree. In this paper, we first introduce a load balancing method of network coding as an alternative use to the max-flow transmission. Next, we study the feasibility of network coding based multicast architecture from performance aspect and evaluate the network coding in terms of the max-flow and load balancing with a computer simulation. There has been no evaluation of network coding in practical network environment with packet losses and propagation delay. We also describe required key techniques and technical problems to implement network coding on the current IP networks. Our results will offer valuable insight for designing the future Internet with higher and more effective network utilization.

Web of Science

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

TCP/IP is a key technology in the next generation mobile communication networks. A significant amount of wireless traffic will be carried in the Internet, and wireless connections will have to share network resources with wired connections. However, in a wireless network environment, TCP suffers significant throughput degradation due to the lossy characteristic of a wireless link. Therefore, to design the next generation mobile networks, it is necessary to know how much the wireless connection suffers from the degradation in comparison to the wired connection. In this paper, we discuss the fairness issue between TCP connections over wireless and wired links, and theoretically analyze the fairness of throughput between TCP over wireless link with ARQ (Automatic Repeat reQuest)-based link layer error recovery and TCP over error-free wired link. We validate our analysis by comparing the numerical results obtained from the analysis with the results obtained from computer simulation. The numerical results show that the fairness is sensitive to network propagation delay and variation rapidity of wireless link characteristic. We also obtain the theoretical lower bound of fairness.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

One of the most important technical problems in reliable multicast protocol is reducing redundant feedback information, e.g. NAKs, to avoid feedback implosion. A number of feedback suppression mechanisms have been proposed to deal with this problem. In the MBONE, which is a virtual multicast network and makes multi-point communication across the Internet feasible, the source link, the links directly connected to or very close to the source, is reported to contribute high percentile packet loss. When a well-known NAK suppression mechanism is applied, in the case of the source link loss, all receivers suffer the same packet loss and NAK suppression mechanism does not work effectively. In this paper we propose a Reliable Multicast Protocol Applying Local FEC, called Local FEC, where the source link loss is recovered with FEC applied locally only to the source link. To investigate performance of our proposed protocol, it is compared with a popular reliable multicast protocol with NAK suppression mechanism. Our performance analysis results with mathematical analysis and Computer simulation show that our proposed protocol outperforms the NAK suppression protocol from the viewpoint of scalability and wasted bandwidth.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

There have been few studies evaluating the dominant factor responsible for generating self-similar network traffic while many researchers have discussed the causes of self-similarity. In this paper, we have isolated and compared the effects of the application, transport and network layers on the self-similarity of TCP flows and their aggregates. With a simple computer simulation scenario, we show that in networks where congestion frequently occurs the transport layer dominates the self-similarity of single TCP flows over the application layer. Next we focus on the interactions between the transport and network layer. We show that on high packet loss rates the exponential backoff technique of the TCP is responsible for the elevated level of self-similarity while on low packet loss rates, the synchronization between the TCP flows may induce high degree of self-similarity of the aggregated TCP sessions. To support this conjecture on synchronization, we show synchronization is only present when the TCP flows of the the aggregate operate mostly in congestion avoidance mode.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：SPRINGER-VERLAG BERLIN  

Large parts of the Internet are still incapable of native multicast, and ubiquitous deployment of multicast will take a long time. There are two approaches to provide wide-area multicast service in today's Internet. One is tunneling approach and the other is application-level multicast approach. In this paper, we focus on application-level multicast approach and propose a new scheme which improves the performance penalties of application-level multicast by making use of network support. Because in application-level multicast, endhosts provide multicast functionality instead of routers, application-level multicast delivery tree is inherently less efficient than IP multicast tree. Therefore, in our scheme, the router on the application-level multicast delivery tree alters the tree based on network-level delivery path. We evaluate our scheme with simulation experiment. Our simulation results indicate that our scheme improves the performance of application-level multicast. Further we compare our scheme to the tunneling approach from the viewpoint of transmission performances. The results reveal applicable domains of both approaches.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

TCP traffic has been reported to have not only self-similarity but multi-fractal nature. Multi-fractal nature of traffic volume, in general, is well known to have significant influence to queueing behavior in short time scale. In the paper, we investigate about "what component of TCP congestion control mechanism affects to multifractal nature of generated traffic?". We artificially divide TCP congestion control mechanism to several components and evaluate multi-fractal nature of generated traffic based on multi-fractal scaling analysis. Our simulation results show that Retransmission Time Out mechanism plays an important role for multi-fractal nature of TCP traffic.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In the Internet, the explosive increase of the number of users requires one-to-many information distribution tools. Multicast is one of the most promising ways. One of the most important technical problems of multicast communications in the Internet is the increase of forwarding table entries with the increase of multicast groups. CIDR effectively used for unicast communications cannot be applied to multicast communications because a multicast address is a virtual address. In this paper, we propose a new multicast group aggregation technique where a shared tree aggregates several multicast groups with taking account of redundant traffic volumes in a shared tree. Simulation results show that our proposed scheme can effectively reduce multicast forwarding table entries in a backbone router with small overhead of redundant data transmission in a shared tree.

Web of Science

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

researchmap

Hosted by Prof. Biplab Sikdar

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In the paper, we propose a congestion control scheme for reliable multicast communication which enables TCP fairness and prevents a drop-to-zero problem. The proposed congestion control scheme is rate-based one based on NAKs from receivers and cooperatively works with a flow control scheme. The congestion control scheme consists of two components of a rate-based controller and a selection mechanism of a representative. The rate-based controller runs between the sender and the representative and achieves TCP fairness and fast response to losses at the representative. The selection mechanism of the representative allows the sender to select the representative in a scalable manner, in which the sunder makes use of NAKs from receivers to select it. In the paper, we also propose the switchover mechanism of the flow and congestion control schemes which enables the sender to use either of them adaptively based on network situations. When the network is congested, the congestion control scheme works to share network resources fairly with competing TCP flows. Otherwise, the flow control scheme works to adapt the transmission rate to the slowest receiver. We verify the performance of our proposed schemes by using computer simulation.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In content distribution networks(CDNs), the content routing which directs user requests to an adequate server from the viewpoint of improvement of latency for obtaining contents is one of the most important technical issues. Several information, e.g. server load or network delay, can be used for content routing. Network support, e.g. active network, enables a router to select an adequate server by using these information. In the paper, we investigate a server selection policy of a network support approach from the viewpoint of which information to be used for effective server selection. We propose a server selection policy using RTT information measured at a router. Simulation results show that our proposed server selection policy in content routing selects a good server under both conditions where server latency and network delay is a dominant element of user response time. Furthermore, we also investigate about location of routers with network support bringing good performance for our proposed scheme.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

A significant amount of wireless traffic will be carried in the Internet, and wireless connections need to share the network resources with wired connections. However, in a wireless network environment, TCP, one of the most important transport protocol of TCP/IP, suffers from significant throughput degradation due to the lossy characteristics of a wireless link. Therefore, in order to design the next generation mobile networks, it is necessary to know how much the wireless connection suffers from the degradation in comparison to the wired connection. In this paper, we discuss the fairness issue between TCP connections over wireless and wired links, and theoretically analyze throughput fairness between TCP over wireless link with ARQ(Automatic Repeat reQuest)-based link layer error recovery and TCP over error-free wired link. We validate our analysis by comparing numerical results obtained from the analysis with computer simulation ones.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

A content distributing algorithm based on market models for a replication distribution scheme of Web contents is proposed. In general, replication distribution is considered to effectively utilize the time and space local properties of access from a client and has been the topic of numerous studies. However, maintaining QoS (such as shortening the content obtaining time) in replicated servers when servers are in a congested state has not been considered in these studies. Since replicated servers constitute a resource shared by multiple ISPs (Internet Service Providers), the accesses need to be limited to replicated servers in case of a congested state to maintain the QoS enjoyed by each client. Thus, in this paper, a scheme for determining allocation of access to replicated servers for each content during congestion based on market models is proposed. The analytical and simulation results have confirmed that the proposed method controls the QoS in accordance with the access arrival rate to each content.

DOI： 10.1002/ecjb.1068

Scopus

researchmap

researchmap

researchmap

researchmap

researchmap

Language：English   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In this paper, we evaluate the performance of flow control mechanisms for reliable multicast under several retransmission approaches in terms of scalability. The mechanisms examined are a window-based flow control mechanism for ACK-based retransmission approaches and a rate-based How control mechanism for NAK-based retransmission approaches. Our simulation results show that the NAK-based flow control mechanism has better scalability and higher throughput than the ACK-based flow control mechanism, and the delay incurred by a NAK suppression mechanism does not affect the performance of multicast flow control.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In server load balancing where replicated servers are dispersed geographically and accesses from clients are distributed to replicated servers, a way of distributing the accesses from clients to an adequate server plays an important role from the viewpoint of load balancing. In the paper, we propose a new network paradigm for server load balancing using active anycast. In active anycast, an end user only sends its request to group of servers using an anycast: address. When this request arrives at an active router, it selects an adequate sur ver from the viewpoint of load balancing and changes the anycast address of a packet to the unicast address of the selected server. The decision which server is the best one from the viewpoint of server load balancing is made by an active router rather than an end user, so active anycast is a network-initiated method. Simulation results show that active anycast can accomplish efficient server load balancing, even when a small Dart of routers are equipped with active network technology.

Web of Science

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

One of the most important technical problems in reliable multicast protocol Is reducing redundant NAKs to avoid NAK implosion. A number of NAK suppression mechanisms have been proposed to deal with this problem. In the MBONE, which is a virtual multicast network and makes multi-point communication across the Internet feasible, the source link, the links directly connected to or very close to the source, contributes 5% packet loss. In NAK suppression mechanism, in the case of such a loss, the source link loss, all receivers suffer the same packet loss and NAK suppression mechanism does not work effectively. In this paper we propose a Reliable Multicast Protocol Applied Local FEC, called the local FEC, where the source link loss is recovered with FEC applied locally only to the source link. To investigate performance of the local FEC, it is compared with reliable multicast protocol with conventional NAK suppression mechanism. Our simulation results show that the local FEC outperforms the NAK suppression protocol from the view point of scalability and wasted network bandwidth.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Recent measurement showed that self-similar nature is found not only in network traffic volume but also round trip packet delay. In this paper, we discuss three issues of the self-similarity of round trip time (RTT), which is one of the most important parameters to determine TCP throughput performance. First, we discuss the origin of the packet delay self-similarity. A recent study anticipated that the queueing delay of self-similar traffic is the reason for packet delay self-similarity. With computer simulation, we evaluate the correlation between traffic and RTT self-similarity. Next, we investigate the impact of RTT self-similarity on TCP throughput performance. Computer simulation results show that RTT self-similarity gives high variability to file transfer time. Finally, we investigate the impact of RTT self-similarity on RTO (Retransmission Time Out). We discover that the bigger the Hurst parameter of RTT is, the more frequent unnecessary timeouts occurs. Furthermore, we propose a new RTO calculation algorithm to improve these unnecessary timeouts.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

Recent measurement showed that self-similar nature is found not only in network traffic volume but also round trip packet delay. In this paper, we discuss three issues of the self-similarity of round trip time (RTT), which is one of the most important parameters to determine TCP throughput performance. First, we discuss the origin of the packet delay self-similarity. A recent study anticipated that the queueing delay of self-similar traffic is the reason for packet delay self-similarity. With computer simulation, we evaluate the correlation between traffic and RTT self-similarity. Next, we investigate the impact of RTT self-similarity on TCP throughput performance. Computer simulation results show that RTT self-similarity gives high variability to file transfer time. Finally, we investigate the impact of RTT self-similarity on RTO (Retransmission Time Out). We discover that the bigger the Hurst parameter of RTT is, the more frequent unnecessary timeouts occurs. Furthermore, we propose a new RTO calculation algorithm to improve these unnecessary timeouts.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In reliable multicast communications, retransmission control plays an important role from the viewpoint of scalability. Previous works show that the implosion of control packets, e.g. ACKs or NAKs, degrades the total performance of reliable multicast communications. Local recovery which enables receivers receiving a packet successfully to initiate recovering a lost packet may have the possibility to solve this scalability problem. This paper presents the performance evaluation of local recovery caused LS grouping receiving nodes in reliable multicast communication. There seems to be many features dominating the performance of local recovery, the number of nodes in a group, the shared loss occurring simultaneously at multiple receivers and so on. When the number of receivers in a group increases, the geographical expansion of a group will degrade the delay performance of the receivers. In a configuration where most nodes in a local-reca cry group suffer from shared loss, the failure of local recovery degrades the total performance. Our simulation results under a hierarchical network topology like the real Internet show that a local-recovery group configuration with two-adjacent MANs grouping performs well.

Web of Science

researchmap

researchmap

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In this paper, we evaluate the performance of flow control schemes for reliable multicast under several retransmission approaches in terms of scalability. The schemes examined are a window-based flow control scheme for ACK-based retrasnmission approaches and a rate-based flow control sheme for NAK-based retransmission approaches. Our simulation results show that the NAK-bascd flow control scheme has better scalability and higher throughput than the ACK-based flow control scheme, and the delay incurred by a NAK-suppression mechanism does not affect the performance of multicast flow control.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

One of the most important technical problems in reliable multicast protocol is to reduce redundant control packets and retransmitted packets. An approach for reducing them by making use of newly-invented network architecture, the active network technology, has been proposed. In the paper we compare a network-initiated approach, i.e. reliable multicast protocol with network support, and conventional end-to-end approaches. These are compared under more realistic situation such as part of routers are equipped with the newly-invented active network technology. Our simulation results show that network-initiated approach with 15% active routers outperforms conventional end-to-end approaches from the viewpoint of scalability. We also investigate desirable location of active routers with sophisticated network topology model, Tiers model, which reflects hierarchical structure of the Internet. Our simulation results suggest that at first active routers should be implemented in I VAN because delay performance can be improved with small number of active routers. After active routers are broadly implemented in WAN, policy for location of active router should be switched to MAN with expecting decrease of redundant NAK transmission inside a network.

Web of Science

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

This paper presents a performance evaluation of NAK-based reliable multicast communication protocols operating in an environment where end-to-end delay are heterogeneous. In the case of heterogeneous delay, performance of a timer-based retransmission control scheme may become worse. We show that a counter-based retransmission control scheme works well in the case of heterogeneous transmission delay. We also compare two NAK-based protocols and show that a NAK-multicasting protocol outperforms a NAK-unicasting protocol from the viewpoint of scalability even when delays are heterogeneous.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：SPRINGER-VERLAG BERLIN  

In reliable multicast communications, transmission rate of a sender should be restricted to the node capability of the lowest node in order to support reliable transmission of packets to all receivers in a multicast group. Even a node of high capability should receive packets at lower rate when there are lower capability nodes in a corresponding multicast group, In reliable multicast communications, heterogeneity of node capability degrades total performance of a multicast group. In the paper, we present the layered multicast group construction, which is one of technical solutions for performance degradation caused by heterogeneity. The basic concept of the layered multicast group construction is to divide a multicast group into multiple subgroups and order them based on node capability. This reduces diversity of node capability inside each sugbroup, which improves delay performance of a whole multicast group. We investigate optimal construction of the layered multicast group construction, i.e. optimal dividing points of subgroups. Numerical examples show that average delay performance is remarkably improved by the layered multicast group construction compared with a conventional single multicast group construction and performance improvement obtained by two or three subgroups is sufficient for practical use.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：SPRINGER-VERLAG BERLIN  

In reliable multicast communications, transmission rate of a sender should be restricted to the node capability of the lowest node in order to support reliable transmission of packets to all receivers in a multicast group. Even a node of high capability should receive packets at lower rate when there are lower capability nodes in a corresponding multicast group, In reliable multicast communications, heterogeneity of node capability degrades total performance of a multicast group. In the paper, we present the layered multicast group construction, which is one of technical solutions for performance degradation caused by heterogeneity. The basic concept of the layered multicast group construction is to divide a multicast group into multiple subgroups and order them based on node capability. This reduces diversity of node capability inside each sugbroup, which improves delay performance of a whole multicast group. We investigate optimal construction of the layered multicast group construction, i.e. optimal dividing points of subgroups. Numerical examples show that average delay performance is remarkably improved by the layered multicast group construction compared with a conventional single multicast group construction and performance improvement obtained by two or three subgroups is sufficient for practical use.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

One of the objectives of ABR traffic control is a fair allocation of transmission rate to every connection. Algorithms which have been proposed can achieve the fair allocation of transmission rate in persistent traffic. even though the connections have different number of hops. In bursty traffic, however, the transmission rate during the burst period, called average burst throughput, may become degraded when the number of hops increases. In this paper, we evaluate the average burst throughput characteristics of ERICA switch algorithm and investigate the effect of the number of hops. We propose a new bandwidth allocation method which can improve the performance degradation by taking the number of hops into account. The effectiveness of our method is evaluated by computer simulation.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

One of the objectives of ABR traffic control is a fair allocation of transmission rate to every connection. Algorithms which have been proposed can achieve the fair allocation of transmission rate in persistent traffic. even though the connections have different number of hops. In bursty traffic, however, the transmission rate during the burst period, called average burst throughput, may become degraded when the number of hops increases. In this paper, we evaluate the average burst throughput characteristics of ERICA switch algorithm and investigate the effect of the number of hops. We propose a new bandwidth allocation method which can improve the performance degradation by taking the number of hops into account. The effectiveness of our method is evaluated by computer simulation.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

DQRUMA ( Distributed-Queueing Request Update Multiple Access) protocol has been proposed as an access protocol for the wireless ATM Local Area Networks. DQRUMA protocol is useful to transmit fixed-length pac packets (e.g. ATM cells). However, it cannot be applied to multimedia environment because it does not include any access control policy for multimedia traffic. In the paper, we propose a slot assignment scheme of DQRUMA protocol in wireless ATM LAN which supports integrated multimedia traffic with different service requirements. In this scheme we can allocate network resources according to the service requirements of each medium because the base station assigns Transmit-Permission flexibly according to the features of each medium.

Web of Science

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In reliable multicast communications, lost information due to packet loss should be re-multicasted. NAK-based retransmission scheme is said to be effective for scalable reliable multicast communications because it can avoid implosion of control packet. When the source sends packets faster than receiver's capacity, packet loss due to buffer overflow occurs constantly at corresponding receivers. With this constant packet loss, implosion of control packet degrades total throughput seriously even in the case of NAK-based retransmission scheme. In order to prevent this kind of constant packer loss at receivers, flow control scheme should be implemented for reliable multicast communications. Iii the paper we propose a new flow control scheme, which is suitable for NAK-based retransmission scheme. From the viewpoint of flow control, receiving a NAK intends that transmission rare is too high. However; in multicast communications, multiple NAKs may be generated for a corresponding packet. If simply receiving a NAK decreases the transmission rate, rate may be decreased excessively In the paper, log information of transmission rate stored at the sender is proposed in order to prevent the transmission rate from decreasing excessively. Performance evaluation by computer simulation shows that our proposed scheme notably improves through put performance compared with the case of no flow control.

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：IEEE  

In reliable multicast communications, lost information due to packet loss should be re-multicasted. NAK-based retransmission scheme is said to be effective for scalable reliable multicast communications because it can avoid implosion of control packet. When the source sends packets faster than receiver's capacity, packet loss due to buffer overflow occurs constantly at corresponding receivers. With this constant packet loss, implosion of control packet degrades total throughput seriously even in the case of NAK-based retransmission scheme. In order to prevent this kind of constant packer loss at receivers, flow control scheme should be implemented for reliable multicast communications. Iii the paper we propose a new flow control scheme, which is suitable for NAK-based retransmission scheme. From the viewpoint of flow control, receiving a NAK intends that transmission rare is too high. However; in multicast communications, multiple NAKs may be generated for a corresponding packet. If simply receiving a NAK decreases the transmission rate, rate may be decreased excessively In the paper, log information of transmission rate stored at the sender is proposed in order to prevent the transmission rate from decreasing excessively. Performance evaluation by computer simulation shows that our proposed scheme notably improves through put performance compared with the case of no flow control.

Web of Science

researchmap

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E, COMPUTER SOC PRESS  

A growing number of network applications require the use of a reliable multicast protocol to disseminate data from a source to a potentially large number of receivers. This paper presents an analytic performance analysis of the packet delay incurred under three generic sender-and receiver-initiated approaches towards reliable multicast. We focus on the host processing requirements of these protocols and derive expressions for average time between the initial arrival of a packet at a sender and its correct reception at a randomly chosen receiver Our numerical results indicate that a NAK-based protocol that limits NAK generation by intentionally and randomly delaying NAK packets can achieve substantially higher throughput than the other two protocols examined, and can do so without suffering an appreciable higher delay over a range of system parameters.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：John Wiley and Sons Inc.  

The rate-based congestion control is one of the most promising schemes for available bit rate (ABR) service in asynchronous transfer mode-local area networks (ATM-LANs). This paper points out the possibility of goodput degradation when the number of connections through a bottleneck queue increases with the binary feedback-type rate-based congestion control where transmission rate is changed on the basis of additive increase-multiplicative decrease principle. Then, to overcome this problem, a feedback-type rate-based congestion control with adaptive parameter is proposed in which rate incremental factor is adapted according to the number of active connections which can be detected by observing the fluctuation of queue length. Simulation results show that the proposed scheme has fine power characteristics for any number of connections sharing the bottleneck node.

DOI： 10.1002/(sici)1520-6424(199702)80:2<44::aid-ecja5>3.0.co;2-a

Scopus

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：JOHN WILEY & SONS LTD  

In this study, we investigate the problem of accommodating multicast traffic in ATM networks, with emphasis on the virtual path (VP) environment. We propose a network structure called ''virtual copy network'' that is suitable for multicast communication and connection setup scheme, taking into account the VP environment. With our technique, we can expect statistical multiplexing gain in accommodating multiple multicast traffic streams over a VP. Also, we propose two multicast routing algorithms (the CNR-LH algorithm and the improved CNR-LH algorithm) for an ATM network environment. In these algorithms, in addition to determining an adequate route, the exact corresponding VPs on the route are also obtained. We examine the efficiency of the algorithms by demonstrating their basic characteristics using computer simulations.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

The message level performance of error controls in data communication on ATM network is analyzed. Three layers, ''a cell''(a unit of transmission), ''a block''(a unit of error controls) and ''a message''(a unit of transmission of user level) are considered. The error controls treated in this paper are GBN (Go-Back-N) and FEC+GBN. The cell loss process is assumed to be the two stale Markov chain considering the cell loss process in ATM networks. Numerical results show that (1) the improvement of the message forwarding delay is saturated in some environments when the interface rate becomes high, (2) FEC is efficient when the burstiness of the cell loss process is small, the message length is large and the interface rate is high.

Web of Science

researchmap

researchmap

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

The optical ATM transport networks are the key technology for B-ISDN which integrates wide variety of communication services. In a photonic ATM switch, electronically operated switching control drastically limits the total throughput. With this bottleneck of the control speed of the switch compared to the cell transmission speed, if the unit of switching operation can be made longer, the system throughput will be improved. This paper proposes the optical backbone network configuration to obtain traffic concentrating effect to construct a large switching unit called a multi-cell. In the backbone network applied the concept of virtual path set (VPS), a multi-cell is constructed by cells from all of ATM switches in a regional network connected with each own's cross connect. The multi-cell format in the case of two different network models is investigated in this paper. The average delay and average idle cells per multi-cell in the multi-cell MUX of an optical cross connect are evaluated by computer simulation as the performance of the multi-cell transfer scheme in the backbone network. Simulation results show that the multi-cell transfer scheme can be operated efficiently with traffic load of more than 0.5. This paper also proposes the configuration of multiplexing and demultiplexing module to assemble and disassemble the multi-cell.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：SCRIPTA TECHNICA PUBL  

This paper considers the shared output buffer-type switching system as an architecture suited to the large-scale ATM switching system. An architecture is proposed, which can solve the fair throughput assignment problem among the ports belonging to the same shared memory, which is a problem in sharing the output buffer. The proposed architecture realizes fair access to the destination port contained in the specified shared buffer, by sort processing and the address attachment, without using the random access contention unit to the buffer in the knockout switch.
For the proposed architecture and the conventional shared output buffer-type knockout switching system, the performances are compared by deriving the cell loss probability due to the output contention for each port. As a result, it is verified that the proposed architecture is better in terms of the realized cell loss probability.
The performance of the switching system is evaluated by a computer stimulation when various buffering schemes are applied to the shared output buffer. Then it is shown that the fair throughput assignment among the considered output ports can be realized by combining the proposed architecture with an adequate buffering scheme.

Web of Science

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E  

Web of Science

researchmap

researchmap

Language：English   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

A new transfer mode and a switching architecture which can support loss free and no delay jitter service class with shorter switching delay compared with ''stop and go queueing scheme'' is proposed. This scheme combines ATM scheme with hierarchical STM framing concept.

Web of Science

researchmap

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E, COMPUTER SOC PRESS  

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E  

Web of Science

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E, COMPUTER SOC PRESS  

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG  

In this paper, we propose a new network organizing method for packet radio networks, a layered self-organizing method. In the layered self-organizing network, whole service area is divided into multiple sub-areas and one base station is settled in each sub-area. Communication links are settled in shorter time than the conventional self-organizing method. We evaluate the network organizing performance of the method by using simulations.

Web of Science

researchmap

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：I E E E  

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC  

In this paper, we propose a new ATM switch architecture which uses the broadcasting transmission medium for transmission of cells from input ports to output ports. Cell transmission and its control are separated completely and cell transmission control, i.e., header operation, is executed before cell transmission (control ahead). By this operation, cell transmission and its control can be executed in pipeline style. This enables high-speed cell exchange and makes transmission control easier. One of the essential problems for ATM switches which use the broadcasting transmission medium is high-speed operation of the transmission medium. We analyze the switch fabric performance according to its switching speed. Numerical results show that the ATM switch proposed here shows good cell loss performance even when its switching speed is restricted, provided that switch utilization is below 1. Furthermore, we show some extension for the switch leads to robustness against bursty traffic.

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：IEICE-INST ELECTRON INFO COMMUN ENG  

Multicast routing problem is one of the essential problems for supporting multicast and broadcast communication service which is the most important service of the multimedia information networks. Multicast routing is the problem of finding out an adequate path which connects one source node and more than one destination node, i.e. a tree shaped path. In packet type networks, a packet for multicast communication should go through the tree shaped path as making its copies at a branching node for efficient use of network resources. However, concentration of packet copy operations at a particular node leads to performance degradation of other calls which go through this node. In this paper we propose two multicast routing algorithms which distribute packet copy operations through whole nodes in the multicast path; a link added type algorithm and a loop constructed type algorithm. Both algorithms, at first, find out an approximate solution for minimum cost path, and avoid concentration of packet copy operation at a little sacrifice of total cost in the path. Computer simulation results show that these algorithms can decrease the burden of packet copy operation per a node at the sacrifice of increase in average distance(cost) of a source-destination pair but the sacrifice of total cost is very small.

Web of Science

researchmap

Language：Japanese   Publisher：電子情報通信学会通信ソサイエティ  

CiNii Books

researchmap

researchmap

researchmap

Hosted by Prof. James F. Kurose

researchmap

researchmap

Language：Japanese   Publisher：電子情報通信学会  

CiNii Books

researchmap

Language：Japanese   Publisher：電子情報通信学会  

CiNii Books

researchmap

researchmap

researchmap

researchmap

researchmap

解説記事

researchmap

解説記事

researchmap

researchmap

researchmap

解説記事

researchmap

researchmap

解説記事

researchmap

解説記事

researchmap

researchmap

J-GLOBAL

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：English  

CiNii Books

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In content-oriented networks, a router can have multiple entries for the same content name when multiple content custodians provide the same content. When an interest packet finds multiple entries at a router on its path, routing strategy which selects one entry for forwarding the interest packet plays an important role for efficient content retrieval. In this paper, we propose a new content routing method, probabilistic content-oriented routing with measured RTT. In our proposed method, selection probability of a routing entry is calculated based on measured RTT so that an interface giving smaller RTT has larger probability to be selected. Our performance evaluation shows that our proposed method can distribute interest packets effectively to multiple content servers, which leads to small content retrieval delay.

CiNii Books

researchmap

Language：Japanese   Publisher：National Institute of Information and Communications Technology  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Technologies for communication in the disaster cases is one of the hot research topics. If users lost connectivity to the Internet due to a large-scale disaster (e.g., earthquake), they can't resolve URL via DNS and retrieve contents such as safety messages from servers in the Internet. We try to adapt CCN(Content-Centric Networking) to fragmented networks that persistently have intermittent links, so-called DTN. However, CCN assumes well-connected wired network with very short RTT. Because CCN has no suitable retransmission mechanism for fragmented networks, redundant retransmission for contents request occurs. Consequently such retransmission causes waste of limited network resources, many packet losses and large power consumption. In this paper, we proposes retransmission suppression mechanism suitable for fragmented networks in disaster scenario that is efficient for both networks and users in terms of energy and resources.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Breadcrumbs has been proposed for in-network guidance towards cached contents. We have also proposed extended-Breadcrumbs, named multi-Breadcrumbs, where a router is allowed to store not only the most recent download direction but also slightly old ones. In this paper, we focus content discovery function of multi-Breadcrumbs and propose Throughput Sensitive content selection method where content receiver selects the best content which provides the best bottleneck throughput. Our simulation results reveal that our proposed Throughput Sensitive content selection method improves throughput of not only popular contents but also non-popular contents. Improvement of non-popular contents is brought by effective traffic distribution towards popular content which gives link bandwidth room for non-popular content.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In content distribution services, such as CDN, a user is interested only in "what content he/she obtains" and not in "where content is retrieved from". This content-oriented feature of content distribution strongly encourages research for content oriented networks. In content oriented networks, network infrastructure itself has content oriented feature and has seamless architectural design concept with content distribution services. In this paper, current research trends in this content oriented network are carefully introduced. First, NDN(Named Data Networking), one of the promising content oriented network architectures, is briefly introduced. And some interesting approaches for router design and caching are explained in detail.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In content distribution services, such as CDN, a user is interested only in "what content he/she obtains" and not in "where content is retrieved from". This content-oriented feature of content distribution strongly encourages research for content oriented networks. In content oriented networks, network infrastructure itself has content oriented feature and has seamless architectural design concept with content distribution services. In this paper, current research trends in this content oriented network are carefully introduced. First, NDN (Named Data Networking), one of the promising content oriented network architectures, is briefly introduced. And some interesting approaches for router design and caching are explained in detail.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

QCN(Quantized Congestion Notification) is proposed for layer 2 congestion control in data center networks. We have proposed QCN/BS(QCN with Bottleneck Selection) which resolves excessive rate regulation problem caused by too many feedbacks from multiple bottleneck links. In this paper, we evaluate QCN/BS in unicast communications with tandem multiple bottleneck links. Our evaluation results surprisingly show that throughput of a long flow going through multiple bottleneck links is degraded. In this paper, we carefully investigate the reason for this fairness problem. And we also show our proposed rate increase algorithm for QCN can reasonably improve fairness of this long flow.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In wireless multi-hop networks, content download traffic from the content server located outside a wireless network is transmitted through the gateway node(GW). Not only content query traffic but also download traffic is transmitted through GW, which causes throughput degradation of a whole wireless network. One promising approach for this technical problem is cache network where all nodes have cache for content file. And Breadcrumbs(BC), in-network guidance method for content query, which can resolve default-path limitation of cache hit, is also another promising approach. In this paper, we evaluate these cache network approaches in wireless multi-hop network environment. Our performance evaluation results reveal that BC significantly improves total throughput. And throughput for not only high popular content but also even medium or low popular content is improved by BC.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Cache network is one of the promising approaches for effective content distribution. In-network guiding technique, Breadcrumbs, where content requests are re-directed towards content download direction has been proposed. In Breadcrumbs, content requests are initially forwarded by a location ID and this property enables the Breadcrumbs systems to be deployed gradually. In this paper, we evaluate the performance of partially deployed Breadcrumbs by using 3-Tier topology model. We also propose two deployment strategies, upper-layer-first strategy and lower-layer-first strategy. Our careful evaluation for these two strategies shows that upper-layer-first strategy gives significant improvement of Breadcrumbs performance even with small deployment.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

QCN (Quantized Congestion Notification) is Layer 2 congestion control in data center network. QCN controls sender's transmission rate with feedback information from a congested switch. We have already revealed that there are sender(s) that cannot receive any feedback frame during congestion period due to probabilistic feedback transmission behavior when the number of flows going through a congested link increases, which causes unstable queue length behavior. To resolve this technical problem, we proposed QCN/DC which integrates QCN with delay-based congestion control. In this paper, we propose new methods for two remained technical problem of QCN/DC; 1) Link utilization becomes low when a new flow joins, 2) RTT threshold for switching between QCN and delay-based congestion control should be adaptively defined. For the former problem, we propose smooth switching which moderately switches transmission rate when transmission rate decision moves from delay-based to QCN. For the latter problem, adaptive threshold computed by measured RTT is proposed. Our simulation results for various scenarios show that our proposed methods regulate queue length fluctuation adequately.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Data center network is composed of high-speed Ethernet extended in a limited area of a data center building, so its RTT is extremely small of μsec order. In order to regulate data center network delay large part of which is queuing delay, QCN is proposed for layer 2 congestion control in IEEE 802.1Qau. QCN controls transmission rate of the sender by congestion feedback from a congested switch. QCN adopts probabilistic feedback transmission to reduce the control overhead. When the number of flows through a bottleneck link increases, some flows might receive no feedback even in congestion phase due to probabilistic feedback transmission. In this situation, queue length might be significantly fluctuated. In this paper, we propose a new delay-based congestion detection and control method. Our proposed delay-based congestion control is cooperated with the conventional QCN so as to detect and react congestion not detected by QCN.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Content accesses to content server providing popular rich contents is now increasing rapidly, which leads to server overload. One of the promising ways to resolve this server overload is caching network. Breadcrumbs(BC)has been proposed for in-network guide information which enables usage of cache not on the default route to the server. In original BC, only the latest download direction is left as BC. However, other removed BC(s) might be useful for search for cached content. In this paper, we evaluate multiple Breadcrumbs which makes use of not only the latest BC but also slightly older BC's. out simulation results show that multiple downloads triggered by multiple queries generated by multiple BC improves server load.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Recently, the amount of traffic on the Internet continues to grow by increment of rich content such as video traffic. Not only the overall traffic volume increases but also the time variation becomes large and the difference in the amount of traffic during the peak time and off peak time is very large. Therefore, it is difficult to use the link bandwidth efficiently. In this paper. we propose a new traffic engineering technique which distributes content distribution traffic both in spatial and time dimensions, named Storage Aware Routing(SAR). SAR can shift content distribution traffic, such as video traffic, in time dimension at each router by using storage with large capacity. So, SAR can route content distribution traffic through a router's outgoing link during its low utilization time period. Our performance evaluation by linear programming formulation shows that SAR can smooth link utilization.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In this paper, we study receiver-driven congestion control for content-oriented services. In content-oriented services, users have no interest in where the content comes and they are just interested in which content is obtained. The current services, e g P2P, enable more sophisticated style of content downloaded from multiple sources In this paper, we propose a new receiver-driven congestion control suitable for content acquisition from multiple sources. In our proposed congestion control, flows sharing the same bottleneck link are controlled in integrated fashion so that they obtain as much throughput as single TCP. Our preliminary simulation results show that our proposed congestion control can share a bottleneck link fairly with single TCP with obtaining reasonable throughput for flows not sharing this bottleneck link.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

When a user obtains a requested content through networks, content location should be explored at first, and content itself should be transferred from this explored location to the user side. In our study, based on the basic idea that a user has no interest in "where content is obtained from" but her interest is just in "what content she obtains," we are developing effective content discovery mechanisms and content transfer mechanisms for new generation networks. Our research is based on Breadcrumbs. Breadcrumbs is in-network guide for cached content and effectively makes use of in-network caches located outside a default-path to the server. In content discovery phase, we focus on load balancing of server and in-network caches. In content transfer phase, we focus on robust and effective content transfer by extending in-network guide function of Breadcrumbs. These our research efforts will open a new research area of new generation content delivery application which enables one of the most important disciplines for content oriented networks, Space Decoupling.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In wireless multi-hop networks having multiple gateways to an external wired network, a host should select its connected gateway when it would like to communicate with an outside host. One possible and simple way is minimum hop gateway selection policy. In our previous study, we have already revealed that when the minimum hop gateway is selected, imbalance of traffic distribution in a network causes significant performance degradation. In our previous work, we have proposed load-balancing gateway selection method which takes account of not only traffic load but wireless interaction around the gateway. Simulation results in simple scenario in our previous work showed that our proposed method improves gateway throughput performance. In this paper, we evaluate our proposed method with more general model. We newly reveal that our proposed method surprisingly improves not only throughput of load-concentrated gateway but also other gateways' throughput by significantly reducing overhead for control packets necessary for route error recovery.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Content transfer, e.g. video transfer, is now becoming major traffic in the current Internet. Content transfer originally has a content oriented feature of "wherever content is retrieved, users only take care of what content they obtain". Conventional traffic engineering aims to obtain optimal routes for traffic between ingress and egress router pairs, which has "location oriented feature, i.e. where to connect". In this paper, we propose a new content oriented traffic engineering, named CAR(Content Aware Routing). Our performance evaluation by linear programing formulation of CAR shows that maximum link utility of CAR can be restricted significantly with slight increase of network resource usage.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

P2P streaming system, such as PPLive and PPstream, is constructed based on the widely deployed BitTorrent P2P system. In BitTorrent, Tit for Tat strategy is used for choking algorithm in order to deal with free rider problem. However, in P2P streaming system, another strategy of unchoking the most uploaded peers is applied because smooth distribution of streaming chunks among peers is very important especially for streaming service. Peers whose offset is going ahead has more chunks to be exchanged than peers with lagged offset, which may lead to imbalance of upload among peers. In P2P system, all peer obtain almost the same amount of information, so fairness of upload amount among peers is one of the most important technical issues. In this paper, we propose a new choking algorithm where each peer tries to select peers with closest offsets as unchoking peers. Our simulation results show that our proposed algorithm boosts chunk exchange among peers with close offsets, which greatly improves fairness among upload of peers.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

For several years, access loads on servers are increasing due to larger contents in content delivery network. One of solving method among the few systems that allow for gradual deployment is the recently-proposed Breadcrumbs technique for distributed coordination among caches in a cache network. When content is downloaded from a server, its direction information, called Breadcrumbs, is stored in routers on a path. When a content request arrives at a router and it has Breadcrumbs for a corresponding content, this request is forwarded to an adequate direction where caching content is expected. In this paper, we evaluate server load improvement performance for partial deployment scenario attention is paid to user and network deployment ratio. We also evaluate server load improvement for Breadcrumbs overlay approach. And performance of non-Breadcrumbs users can be also improved when Breadcrumbs overlay cooperates with underlying networks even as small deployment region.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Among various TCP congestion controls proposed for high delay-bandwidth networks thus far, CUBIC and Compound TCP have been implemented as default congestion control in Linux and Microsoft Windows OS, respectively. CUBIC is loss-based high speed congestion control. Compound TCP is constructed with NewReno TCP and delay-based high speed congestion control. Our previous work showed that throughput Compound TCP is seriously suppressed by CUBIC in high delay-bandwidth wired network environment. In wireless network, these two types of TCPs are also used as default congestion control and expected to fairly share bottleneck link because these two types of TCPs operate in low delay-bandwidth environment. However, with deployment of IEEE 802.11n and LTE, high delay-bandwidth environment is also emerging even in wireless environment. And, in wireless environment, packet loss caused by fading and handover is well known to degrade TCP performance. In this paper, we evaluate fairness issue of CUBIC and Compound TCP in high-speed wireless networks. And we show that unfair condition between these two types of TCPs is relieved in wireless environment because of wireless caused packet loss.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In data center networks, group communication is now playing an important role and multicast communications have been expected an effective way to support group communication for large number of virtual machines. Layer-2 congestion control named QCN (Quantized Congestion Notification) is now proposed for supporting high reliability required by LAN/SAN integration in data center networking. When original QCN is simply applied to multicast communication, a multicast sender may receive congestion feedbacks from multiple bottleneck locations on a multicast tree. In this situation, a multicast flow may suffer lower throughput than unicast flows going through the same bottleneck location(s). In this paper, we propose a new layer-2 congestion control for multicast traffic, QCN with Bottleneck Selection (QCN/BS). In QCN/BS, the switch in the worst congestion level is selected and transmission rate of a sender is calculated only by feedback information sent by this selected switch. Our simulation results show that a multicast sender of original QCN can have severely unfair(less) throughput compared with a unicast sender and our proposed QCN/BS completely resolves this unfair problem.

CiNii Books

researchmap

Language：Japanese  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

There have been proposed lots of improved TCPs, such as several improvements of TCP suitable for wireless networks. With recent trends in networks of high speed and wide bandwidth, TCPs which can highly utilize wide bandwidth have been proposed. Technical problem of TCP with high speed and long distance network is low utilization caused by slow increase and long duration of additive increase phase. Simple improvement of scalability with aggressive increase degrades both TCP friendliness and RTT fairness. Several sophisticate improvements which resolve above three technical problems, scalability, RTT fairness and TCP friendliness, are now implemented in widely used OS, Windows and Linux. This paper comprehensively illustrates these widely deployed TCP new versions and their design principles. And it also shows new fairness problem among different type of high speed TCPs. This paper also explains layer 2 congestion control in data center networks. In data center networks, Ethernet bridges which do not lose frames even under congestion are required, which is significantly more strict requirement than conventional LAN. QCN, a standardized layer 2 congestion control in IEEE 802.1Qau, is explained in detail.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

The primary use of the current Internet is content distribution and it generates large portion of traffic going through the Internet. Communication model has been point-to-point and location-oriented since creation of the Internet. In content distribution, user's concern is content itself and is not a location where it is obtained. From this viewpoint, content oriented-services, such as CDN and P2P, are provided on application layer. However, network itself is still location-oriented and mismatch between higher and lower layers in network protocol introduces large overheads. Recently, content-oriented networks which change communication model to rendezvous one becomes one of hot research topics concerning new generation network. This paper overviews historical background and basic concept of content-oriented networks. It also surveys content oriented-network researches from the viewpoint of content discovery, transport and caching.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

An in-network guidance method, Breadcrumbs, has been proposed for implicit coordination of cache networks. When content is downloaded from a server, its direction information, called Breadcrumbs, is stored in routers on a path. When a content request arrives at a router and it has Breadcrumbs for a corresponding content, this request is forwarded to an adequate direction where caching content is expected. In this paper, we evaluate server load improvement performance for partial deployment scenario of Breadcrumbs routers. We also evaluate server load improvement for Breadcrumbs overlay approach. Our simulation results show that overlay approach significantly decreases invalidation of Breadcrumbs. And performance of non-Breadcrumbs users can be also improved when Breadcrumbs overlay cooperates with underlying networks.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In recent large-scale Data Center, two types of network, LAN and SAN are implemented. In order for simple network management, integration of these two networks by Ethernet technology is now hotly discussed. SAN requires sig-nificantly low frame loss rate. For integration of LAN and SAN, multi-hop Ethernet configuration is generally used and congestion may occur in traffic hot spot. So, layer 2 congestion control which prevents frame loss in multi-hop Ethernet, QCN (Quantized Congestion Notification), is now discussed in IEEE 802.1Qau. In this paper, we evaluate throughput performance of QCN and reveal QCN has technical problem of fairness among active flows. We also reveal that a cause of unfairness is that flow with high transmission rate can increase its transmission rate faster than low transmission rate flow. We propose Adaptive BC-LIMIT for QCN where EC-LIMIT is adaptively decided according to current transmission rate of flows. Simulation results show that our proposed method significantly improves fairness among QCN flows.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Among various TCP congestion controls proposed for high delay-bandwidth networks thus far, CUBIC and Compound TCP have been implemented as default congestion control in Linux and Microsoft Windows OS, respectively. CUBIC is loss-based TCP. Compound TCP is constructed with NewReno TCP and delay-based high speed congestion control. Delay-based TCP is well-known to be suppressed by loss-based TCP when delay-based and loss-based TCP share a bottleneck link. Our simulation results show that Compound TCP is seriously suppressed by CUBIC in high delay-bandwidth network environment. In this paper, we propose a new buffer management which improves fairness issues for Compound TCP and CUBIC.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Technical issues for wireless multihop networks include throughput degradation for long hop sessions, especially for long TCP sessions. One promising way to resolve this technical issue is proxy-based TCP which divides long end-to-end TCP session into several sub-sessions at proxy host(s). We have already shown that proxy-based TCP cannot obtain throughput improvement and also proposed adaptive rate control and intentional flow control which prevent burst segment transmission on divided sub-sessions. In this paper, we evaluate throughput performance of our proposed schemes in multiple flow case. Simulation results show that it obtains better total throughput but has fairness problem for throughput obtained for each flow. We investigates causes for this unfair condition of our proposed schemes and show future research directions for resolving this fairness issue.

CiNii Books

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In recent large-scale data center, two types of network, LAN and SAN are implemented. In order for simple network management, integration of these two networks by Ethernet technology is now hotly discussed. SAN is required significantly low frame loss rate. For integration of LAN and SAN, multi-hop Ethernet configuration is generally used and congestion may occur in traffic hot spot. So, layer 2 congestion control which prevents frame loss in multi-hop Ethernet, QCN(Quantized Congestion Notification), is now discussed in IEEE 802.1Qau. In this paper, we evaluate throughput performance of QCN and reveal QCN has technical problem of fairness among active flows. We also propose a new "Target Rate Initialization method" which improves fairness among flows and show its effectiveness by computer simulation.

CiNii Books

researchmap

researchmap

researchmap

Language：Japanese   Publisher：東京 : 電子情報通信学会通信ソサイエティ  

CiNii Books

researchmap

Other Link： https://ndlsearch.ndl.go.jp/books/R000000004-I10577796

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

Language：Japanese   Publisher：東京 : 電子情報通信学会  

CiNii Books

researchmap

Other Link： https://ndlsearch.ndl.go.jp/books/R000000004-I9673877

J-GLOBAL

researchmap

researchmap

Language：Japanese   Publisher：東京 : 情報処理学会  

CiNii Books

researchmap

Other Link： https://ndlsearch.ndl.go.jp/books/R000000004-I9524867

Language：Japanese   Publisher：東京 : 電子情報通信学会  

CiNii Books

researchmap

Other Link： https://ndlsearch.ndl.go.jp/books/R000000004-I9527755

researchmap

researchmap

researchmap

researchmap

researchmap

チュートリアル講演

researchmap

researchmap

researchmap

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

J-GLOBAL

researchmap

J-GLOBAL

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

Multicast communications have been expected as an effective way to disseminate the same information to potentially large number of receivers. IP multicast is a well-known multicast protocol for the Internet. Deployment of IP multicast depends on wide deployment of the multicast routers in the Internet, which will take extremely long time. In these days, one possible solution which enables multicast service without deployment of multicast routers, application level multicast, has been proposed. In application level multicast, multicast tree is constructed in the overlay network. All nodes in the overlay multicast tree are end hosts which require multicast data. When a packet arrives at a host which is located at a branching point of the overlay multicast tree, this host makes replica of arrived packets and forwards it to the appropriate neighbour overlay node. This means multicast function, such as replication of packet and multicast routing, is provided by an end host rather than a router in the application level multicast. The paper overviews the basic concept of the application level multicast and surveys important approaches for tree construction methods. The paper laso discusses furture direction of the application level multicast.

CiNii Books

researchmap

招待講演

researchmap

researchmap

Language：Japanese   Publisher：Kansai University  

CiNii Books

researchmap

奨励講演

researchmap

researchmap

researchmap

researchmap

researchmap

奨励講演

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In this paper, we discuss TCP congestion control in Wireless Overlay Networks where various access links such as a wireless LAN and a cellular network are integrated. In the Wireless Overlay Network, vertical handover, which is a handover technique between different types of access links, is one of the most important technologies. The vertical handover significantly degrades throughput performance of TCP because it causes drastic change in a bandwidth delay product of each TCP flow. The authors have already proposed an ACK-pacing mechanism for TCP congestion control and evaluated a basic performance with a single node. In this paper, we discuss technical requirement for the proposed system in a more practical environment where there are multiple nodes sharing a wireless link. In this environment, it is necessary to design the ACK-pacing mechanism with taking account of fairness and reduce a waste of network resource due to ACK overhead. Furthermore, we evaluate the performance of the proposed system in the multiple node environment with a simulation.

CiNii Books

researchmap

researchmap

researchmap

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

CiNii Books

researchmap

researchmap

奨励講演

researchmap

researchmap

Language：Japanese   Publisher：The Institute of Electronics, Information and Communication Engineers  

In WDM networks, traffic grooming technique improves wavelength utilization by multiplexing lower rate traffic streams into higher capacity lightpaths. In this paper, we discuss the fairness issue in WDM networks with traffic grooming capabilities (WDM grooming networks). In WDM grooming networks, call requests which ask for capacity nearer to the full wavelength capacity are bound to experience higher blocking than those which ask for a smaller fraction. In this paper, we propose a new dynamic routing and wavelength assignment (dynamic RWA) technique to improve the fairness. In the proposed RWA, call requests are classified into high-speed traffic class and low-speed traffic class according to their traffic demand, and different routing and wavelength assignment policies are applied to each traffic class. Computer simulation results show that the proposed RWA improves the fairness.

CiNii Books

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap