一种新的逐跳TCP友好的主动分层多播拥塞控制方案

基于Internet的多媒体多播应用的迅猛发展对多播拥塞控制提出了要求.分层多播是适应网络异构性较有效的方案.针对现有分层多播存在的问题,将主动网技术思想引入到分层多播拥塞控制中,提出了一种逐跳TCP友好的主动分层多播拥塞控制方案(HTLMA),采用主动标记分层、逐跳探测TCP友好可用带宽,以及主动速率控制机制.仿真实验表明,HTLMA方案大大改进了分层多播拥塞控制的性能,具有较快的拥塞响应速度、较好的稳定性和TCP友好特性.     

Multicasting with Localized Control in Wireless Ad Hoc Networks

This paper investigates how to support multicasting in wireless ad hoc networks without throttling the dominant unicast flows. Unicast flows are usually congestion-controlled with protocols like TCP. However, there are no such protocols for multicast flows in wireless ad hoc networks and multicast flows can therefore cause severe congestion and throttle TCP-like flows in these environments. Based on a cross-layer approach, this paper proposes a completely-localized scheme to prevent multicast flows from causing severe congestion and the associated deleterious effects on other flows in wireless ad hoc networks. The proposed scheme combines the layered multicast concept with the routing-based congestion avoidance idea to reduce the aggregated rate of multicast flows when they use excessive bandwidth on a wireless link. Our analysis and extensive simulations show that the fully-localized scheme proposed in this paper is effective in ensuring the fairness of bandwidth sharing between multicast and unicast flows in wireless ad hoc networks.     

Bandwidth estimation schemes for TCP over wireless networks

The use of enhanced bandwidth estimation procedures within the congestion control scheme of TCP was proposed recently as a way of improving TCP performance over links affected by random loss. This paper first analyzes the problems faced by every bandwidth estimation algorithm implemented at the sender side of a TCP connection. Some proposed estimation algorithms are then reviewed, analyzing and comparing their estimation accuracy and performance. As existing algorithms are poor in bandwidth estimation, and in sharing network resources fairly, we propose TIBET (time intervals based bandwidth estimation technique). This is a new bandwidth estimation scheme that can be implemented within the TCP congestion control procedure, modifying only the sender-side of a connection. The use of TIBET enhances TCP source performance over wireless links. The performance of TIBET is analyzed and compared with other schemes. Moreover, by studying TCP behavior with an ideal bandwidth estimation, we provide an upper bound to the performance of all possible schemes based on different bandwidth estimates.     

Modeling and analysis of TCP-like multicast congestion control in hybrid terrestrial/satellite IP networks

Given their broadcast nature, satellite communications are one natural engineering choice for multicast service deployment. In this paper, the throughput performance of transmission control protocol (TCP)-like multicast congestion control is analyzed in hybrid terrestrial/satellite networks. With this objective, an analytical framework based on Markov chains is introduced. The major advantage of the proposed analytical model is its scalability in that the number of states of the Markov chain modeling the system is independent of the number of receivers in the multicast session. This is a very important feature as simulation is unfeasible for large numbers of receivers. The framework is used to evaluate the impact of the long propagation delays, high bit-error rates, and channel asymmetry characterizing hybrid terrestrial/satellite communications. The performance results show that in certain cases, it is more convenient to divide the receivers in an appropriate number of groups and establish a different multicast session toward each of the above groups. Also, the convenience of an acknowledgment (ACK) flow reconstructor is shown.     

Basestation flow control for wired to wireless networks

With the exponential growth of the internet, wireless networks such as satellite networks are becoming increasingly popular. The characteristics of satellite networks such as long latency, large delay-bandwidth product, high bit error rate over satellite links and variable round trip time, severely degrade TCP/IP performance. At the conjunction of the satellite link and the fixed link, the basestation, the difference in capacity between the satellite link and the fixed link causes the basestation to experience congestion losses that adversely impact TCP performance. We propose a technique that substantially reduces the congestion at the base station and enforces fairness among the TCP connections that are sharing the satellite link. The technique does not require any change in the TCP sender or the receiver. The stability of our algorithm is analytically proven and its performance is evaluated using ns-2 simulations. Preliminary results yield almost a null congestion loss rate, a 60% decrease in average queue length, and more than 30% increase in the throughput. Fairness is well enforced.     

TCP-Peach: a new congestion control scheme for satellite IPnetworks

Current TCP protocols have lower throughput performance in satellite networks mainly due to the effects of long propagation delays and high link error rates. In this paper, a new congestion control scheme called TCP-Peach is introduced for satellite networks. TCP-Peach is composed of two new algorithms, namely Sudden Start and Rapid Recovery, as well as the two traditional TCP algorithms, Congestion Avoidance and Fast Retransmit. The new algorithms are based on the novel concept of using dummy segments to probe the availability of network resources without carrying any new information to the sender. Dummy segments are treated as low-priority segments and accordingly they do not effect the delivery of actual data traffic. Simulation experiments show that TCP-Peach outperforms other TCP schemes for satellite networks in terms of goodput. It also provides a fair share of network resources     

TCP-Peachtree: a multicast transport protocol for satellite IP networks

In this paper, a reliable multicast transport protocol TCP-Peachtree is proposed for satellite Internet protocol (IP) networks. In addition to the acknowledgment implosion and scalability problems in terrestrial wirelined networks, satellite multicasting has additional problems, i.e., different multicast topology, different type of congestion control problems, and low bandwidth feedback link. In TCP-Peachtree, the modified B+ tree logical hierarchical structure is used to form dynamic multicast groups. Local error recovery and acknowledgment (ACK) aggregations are performed within each subgroup and also via logical subgroups. In order to avoid the overall performance degradation caused by some worst receivers, a local relay scheme is designed. Two new algorithms, jump start and quick recovery, which are based on the usage of a type of low-priority segments called NIL segments, are proposed for congestion control. NIL segments are used to probe the availability of network resources and also for error recovery. The delayed selective acknowledgment (SACK) scheme is adopted to address the bandwidth asymmetry problems and a hold state is developed to address persistent fades. The simulation results show that the congestion control algorithms of TCP-Peachtree outperform the TCP-NewReno when combined with our hierarchical groups and improve the throughput performance during rain fades. It is also shown that TCP-Peachtree achieves fairness and is very highly scalability.     

TCP Window Control for Variable Bandwidth in Wireless Cellular Networks

Most of TCP schemes in wireless networks assume that the bandwidth of the bottleneck link remains constant over time. However, in wireless cellular networks, to effectively manage the limited resources, the bandwidth is controlled based on radio condition over time. Such varying bandwidth can cause the networks congestion or underutilization. In this letter, we propose a new window control algorithm to improve TCP performance in wireless cellular networks with variable bandwidth. Simulation results illustrate that our proposal improves the performance of TCP in terms of fairness and link utilization     

Achieving inter-session fairness for layered video multicast

The Internet is increasingly used to deliver multimedia services. Since there are heterogeneous receivers and changing network conditions, it has been proposed to use adaptive rate control techniques such as layered video multicast to adjust the video traffic according to the available Internet resources. A problem of layered video multicast is that it is unable to provide fair bandwidth sharing between competing video sessions. We propose two schemes, layered video multicast with congestion sensitivity and adaptive join-timer (LVMCA) and layered video multicast with priority dropping (LVMPD), to achieve inter-session fairness for layered video multicast. Receiver-driven layered multicast (RLM), layer-based congestion sensitivity, LVMCA, and LVMPD are simulated and compared. Results show both proposed schemes, especially LVMPD, are fairer and have shorter convergence time than the other two schemes.     

A study on a receiver‐based management scheme of access link resources for QoS‐controllable TCP connections

Although the bandwidth of access networks is rapidly increasing with the latest techniques such as DSL and FTTH, the access link bandwidth remains a bottleneck, especially when users activate multiple network applications simultaneously. Furthermore, since the throughput of a standard TCP connection is dependent on various network parameters, including round‐trip time and packet loss ratio, the access link bandwidth is not shared among the network applications according to the user's demands. In this thesis, we present a new management scheme of access link resources for effective utilization of the access link bandwidth and control of the TCP connection's throughput. Our proposed scheme adjusts the total amount of the receive socket buffer assigned to TCP connections to avoid congestion at the access network, and assigns it to each TCP connection according to characteristics in consideration of QoS. The control objectives of our scheme are (1) to protect short‐lived TCP connections from the bandwidth occupation by long‐lived TCP connections, and (2) to differentiate the throughput of the long‐lived TCP connections according to the upper‐layer application's demands. One of the results obtained from the simulation experiments is that our proposed scheme can reduce the delay of short‐lived document transfer perceived by the receiver host by up to about 90%, while a high utilization of access link bandwidth is maintained. Copyright © 2006 John Wiley & Sons, Ltd.     

SLM-一种安全分层组播协议

流媒体分发的一种典型实现方法是采用具有接收方驱动拥塞控制机制的分层组播.由于目前分层组播拥塞控制协议缺乏对用户行为的限制,接收方可违规订阅上层组播组发起自利型攻击,导致非公平的带宽利用.本文提出了一种较通用的安全分层组播协议SLM(Secure Layered Multicast).在路由器辅助拥塞控制条件下,在边界路由器采用基于Shamir秘密共享体制的拥塞状态相关访问控制(CR-AC,Congestion state Related Access Control)算法,管理用户组订阅行为,避免了用户自利型攻击,并使服务提供商可根据其与用户的协约限定不同用户的最高订阅级别.分析和仿真实验表明,该协议可实时保证网络流量安全共享带宽并具有较好的可扩展性.     

改善卫星融合网络随机丢包和间歇性中断的方法研究*1

当移动自组织网用户通过网关经卫星网络发送数据时,存在卫星链路的长传播时延、随机丢包以及移动终端的移动性引起链接的间歇性中断,导致TCP触发拥塞控制机制而降低传输性能降低。针对以上卫星网络的特点,提出了TCP M-Veno方法。在发送端对TCP Veno进行优化改进使得它能够缓解卫星网络中长的传播时延和随机丢包的影响。在网关中结合M-TCP算法来解决卫星融合网络移动终端间歇性中断。仿真表明,所提出的TCP M-Veno比NewReno、Veno以及M-TCP有更好的传输性能。     

面向GEO卫星网络的多速率多播拥塞控制机制

针对GEO卫星网络带宽时延积较大、拥塞控制机制不完善的问题,提出了一种面向GEO卫星网络的多速率多播拥塞控制机制MMCCM_GEO.首先,在保证接收端请求速率最大化的前提下,将GEO卫星网络中的多速率多播问题转化为非线性优化问题,并采用改进的模拟退火算法对其求解,得到了最优的接收端请求速率.其次,通过采用代理节点实现反馈信息的汇集与丢失数据的恢复,有效地解决了反馈内暴及数据恢复问题.仿真结果表明,与目前GEO卫星网络中典型的多速率多播拥塞控制机制相比,本文的拥塞控制机制有效地提高了数据吞吐量和带宽利用率,降低了GEO卫星网络中的数据传输时延,同时也具备了更好的可扩展性.     

Fine-grained Layered multicast with STAIR

Traditional approaches to receiver-driven layered multicast have advocated the benefits of cumulative layering, which can enable coarse-grained congestion control that complies with TCP-friendliness equations over large time scales. In this paper, we quantify the costs and benefits of using noncumulative layering and present a new, scalable multicast congestion control scheme called STAIR that embodies this approach. Our first main contribution is a set of performance criteria on which we base a comparative evaluation of layered multicast schemes. In contrast to the conventional wisdom, we demonstrate that fine-grained rate adjustment can be achieved with only modest increases in the number of layers, aggregate bandwidth consumption and control traffic. The STAIR protocol that we subsequently define and evaluate is a multiple rate congestion control scheme that provides a fine-grained approximation to the behavior of TCP additive increase/multiplicative decrease (AIMD) on a per-receiver basis.     

Improving TCP Vegas Fairness in Presence of Backward Traffic

TCP Vegas provides better performance compared to traditional TCP Reno schemes. However, backward traffic significantly degrades Vegas efficiency causing underutilization of the available bandwidth and unfairness. In this letter, we present an enhanced congestion control mechanism for TCP Vegas able to correctly remove the undesired impact of reverse traffic on bandwidth sharing. Furthermore, our proposal is easily deployable because it does not require neither clock synchronization nor any special support at the intermediate routers     

Protecting TCP from a misbehaving receiver

This study presents the design and implementation of a robust TCP congestion control algorithm. TCP was originally designed for cooperative environments, and its evolution over the years has been built on the same basis. TCP expects the end hosts to cooperate with the TCP senders in implementing end‐to‐end congestion control. Therefore, misbehavior of a TCP receiver may result in an unfair division of the available bandwidth between the conforming flows and the irresponsible flows. Accordingly, this study examines the issues arising when conforming TCP connections are obliged to coexist with misbehaving connections. A modification to the TCP protocol is proposed to deal with various types of TCP misbehavior. Copyright © 2006 John Wiley & Sons, Ltd.     

A cognitive accountability mechanism for penalizing misbehaving ECN‐based TCP stacks

The introduction of high‐bandwidth demanding services such as multimedia services has resulted in important changes on how services in the Internet are accessed and what quality‐of‐experience requirements (i.e. limited amount of packet loss, fairness between connections) are expected to ensure a smooth service delivery. In the current congestion control mechanisms, misbehaving Transmission Control Protocol (TCP) stacks can easily achieve an unfair advantage over the other connections by not responding to Explicit Congestion Notification (ECN) warnings, sent by the active queue management (AQM) system when congestion in the network is imminent. In this article, we present an accountability mechanism that holds connections accountable for their actions through the detection and penalization of misbehaving TCP stacks with the goal of restoring the fairness in the network. The mechanism is specifically targeted at deployment in multimedia access networks as these environments are most prone to fairness issues due to misbehaving TCP stacks (i.e. long‐lived connections and a moderate connection pool size). We argue that a cognitive approach is best suited to cope with the dynamicity of the environment and therefore present a cognitive detection algorithm that combines machine learning algorithms to classify connections into well‐behaving and misbehaving profiles. This is in turn used by a differentiated AQM mechanism that provides a different treatment for the well‐behaving and misbehaving profiles. The performance of the cognitive accountability mechanism has been characterized both in terms of the accuracy of the cognitive detection algorithm and the overall impact of the mechanism on network fairness. Copyright © 2012 John Wiley & Sons, Ltd.     

基于自适应丢包区分的卫星信道TCP改进

通过卫星扩展TCP/IP网络无论在商业还是军事上具有十分重要的意义。但由于链路的高时延、高误码率和严重的信道衰落,使得TCP/IP应用于卫星链路时,相对于有线链路性能较差,因此将TCP/IP应用于卫星链路时,必须对TCP/IP进行改进。提出了自适应特定队列管理的方法,其基本思想是根据网络事件动态调整模式匹配参数,使得在拥塞和卫星链路误码率增加的情况下,都具有较高的丢包区分准确率。     

Leveraging single rate schemes in multiple rate multicast congestion control design

A significant impediment to deployment of multicast services is the daunting technical complexity of developing, testing and validating congestion control protocols fit for wide-area deployment. Protocols such as pragmatic general multicast congestion control (pgmcc) and TCP-friendly multicast congestion control (TFMCC) have recently made considerable progress on the single rate case, i.e., where one dynamic reception rate is maintained for all receivers in the session. However, these protocols have limited applicability, since scaling to session sizes beyond tens of participants with heterogeneous available bandwidth necessitates the use of multiple rate protocols. Unfortunately, while existing multiple rate protocols exhibit better scalability, they are both less mature than single rate protocols and suffer from high complexity. We propose a new approach to multiple rate congestion control that leverages proven single rate congestion control methods by orchestrating an ensemble of independently controlled single rate sessions. We describe a new multiple rate congestion control algorithm for layered multicast sessions that employs a single rate multicast congestion control as the primary underlying control mechanism for each layer. Our new scheme combines the benefits of single rate congestion control with the scalability and flexibility of multiple rates to provide a sound multiple rate multicast congestion control policy.