基于TCP拥塞控制可靠性多播协议的研究

随着互联网规模的增长,互联网上的用户和应用都在快速的增长,拥塞已经成为一个十分重要的问题.由此提出了一个新的协议,称为可靠的拥塞控制多播协议(RCCMP).拥塞控制是该协议的核心,该协议即不需要来自于网络元素的支持,也不需要维持依靠接收者数目的状态信息,并在此研究的基础上也介绍了该协议执行性能的系列仿真结果.     

Generalized multicast congestion control

Efficient multicast congestion control (MCC) is one of the critical components required to enable the IP multicast deployment over the Internet. Previously proposed MCC schemes can be categorized in two: single-rate or multi-rate. Single-rate schemes make all recipients get data at a common rate allowed by the slowest receiver, but are relatively simple. Multi-rate schemes allow of heterogeneous receive rates and thus provide better scalability, but rely heavily on frequent updates to group membership state in the routers. A recent work by Kwon and Byers, combined these two methods and provided a multi-rate scheme by means of single-rate schemes with relatively low complexity.In this paper, we propose a new scheme called generalized multicast congestion control (GMCC). GMCC provides multi-rate features at low complexity by using a set of independent single-rate sub-sessions (a.k.a layers) as building blocks. The scheme is named GMCC because single-rate MCC is just one of its special cases. Unlike the earlier work by Kwon and Byers, GMCC does not have the drawback of static configuration of the source which may not match with the dynamic network situations. GMCC is fully adaptive in that (i) it does not statically set a particular range for the sending rates of layers, and (ii) it eliminates redundant layers when they are not needed. Receivers can subscribe to different subsets of the available layers and hence can always obtain different throughput. While no redundant layers are used, GMCC allows receivers to activate a new layer in case existing layers do not accommodate the needs of the actual receivers.     

TCP拥塞控制算法

针对广泛应用的TCP Reno慢启动算法与拥塞避免算法的问题,在研究分析TCP Reno拥塞控制算法的基础上,提出一种新的拥塞控制算法——在慢启动阶段采用线性增长算法,而在拥塞避免阶段采用基于拥塞窗口的对数增长算法,从而一定程度上解决了TCPReno慢启动不公平问题与拥塞避免阶段拥塞窗口增长过于激进的问题。通过NS仿真实验说明了新算法的可行性,并对其吞吐量、公平性、友好性进行评估,仿真结果表明了该改进的TCP拥塞控制算法的有效性。     

Configurable active multicast congestion control

A multicast congestion control and avoidance scheme is indispensable for group-based applications to fairly share and efficiently use network resources with unicast applications and maintain the stability of the Internet. It is difficult for the traditional pure “end-to-end” solution to address both TCP-friendliness and inter-receiver fairness [T. Jiang, M.H. Ammar, E.W. Zegura, Inter-receiver fairness: a novel performance measure for multicast ABR sessions, in: Proceedings of ACM SIGMETRICS’98; T. Jiang, E.W. Zegura, M. Ammar, Inter-receiver fair multicast communication over the Internet, in: Proceedings of NOSSDAV’99] by using only one multicast group. In this paper, we present a novel active multicast congestion control scheme (AMCC). Significantly different from the popular end-to-end congestion control approach, AMCC is a router-assisted window-based hierarchical one. With flexible configuration of parameters and effective use of network resources such as buffers at the active routers, AMCC cannot only behave as a TCP-friendly single-rate congestion control scheme, but also have the benefits of a multi-rate congestion control scheme to achieve inter-receiver fairness by limiting the effect of congestion on a specific link to a small region. In addition, when it is used with reliable multicast applications, AMCC has the special mechanisms to regulate repair packets, which are not specifically addressed by the previous work. We implement and evaluate our protocol in NS2 [http://www.isi.edu/nsnam/ns/].     

新的TCP拥塞控制机制

拥塞控制已成为确保Internet稳定性、鲁棒性的关键因素.针对目前TCP拥塞控制机制中存在的实际问题,提出了一种新的拥塞控制机制,包括COS-Slow-Start和A-AIMD两种改进策略.NS2仿真实验结果表明,该机制能有效地减少分组的丢失、平缓突发流量的冲击,并可增加带宽的有效利用率.     

基于TCP Vegas的网络拥塞控制改进算法*

由于TCP Vegas在与TCP Reno算法共存的网络环境中不能公平地竞争到带宽,TCP Vegas-A拥塞控制算法有效地改进了TCP Vegas算法在带宽竞争力弱方面的缺陷。对TCP Vegas-A算法进行了仿真研究并提出一种拥塞控制改进算法TCP NewVegas。基于NS2的仿真实验证明TCP NewVegas算法提高了与TCP Reno共存时在网络中的带宽竞争能力。     

TCP Vegas-b:TCP Vegas改进算法

针对TCP Vegas存在的过早结束慢启动进入拥塞避免阶段,导致带宽利用率下降;与TCP Reno共享一条链路时不能公平的竞争到带宽等不足,提出了改进算法TCP Vegas-b。该算法改进了慢启动阶段的窗口增加方式并且在拥塞避免阶段中动态调整、的值。实验结果表明,改进后算法有效的解决了慢启动过早结束的缺陷,提高了吞吐量,并且实现了Vegas和Reno在共存环境下两者良好的兼容性。     

Extending equation-based congestion control to high-speed and long-distance networks

TCP-friendly rate control (TFRC), an equation-based congestion control protocol, has been a promising alternative to TCP for multimedia streaming applications. However, TFRC using the TCP response function, has the same poor performance as TCP in high-speed and long-distance networks. In this paper, we propose high-speed equation-based rate control (HERC), as an extension of TFRC by replacing the TCP response function with a high-speed response function. HERC could be used for applications, such as high-definition video streaming, and remote collaboration involving high-resolution visualization, which prefer a high-speed and relatively smooth sending rate. The impact of a general high-speed response function on the throughput and smoothness of HERC is studied analytically and verified by using simulation. Our result indicates that by using the response function of a high-speed TCP variant and tuning HERC parameters accordingly, HERC can compete fairly with high-speed TCP flows in the same network, while maintaining the desired smoothness of TFRC.     

基于强度控制的并行TCP拥塞控制策略研究

随着网络带宽的不断提升,基于并行TCP的应用方式得到广泛使用。当节点为同一个应用打开多个TCP连接时,对于使用单一TCP连接的网络用户存在严重的不公平。提出一种基于强度控制的并行TCP拥塞控制方案TCP C,使这些TCP流共享拥塞信息,同时限制并行TCP流的有效连接数量,以控制并行流的侵略性。实验结果显示该方案能够较好地保证公平性,同时有效地利用网络带宽。     

一种新型的端到端TCP拥塞控制机制

拥塞控制机制是决定TCP协议性能的重要因素。传统拥塞控制机制在卫星网络中运用时会导致TCP性能的大幅下降。本文提出了一种新的适应于卫星网络大延时特点的端到端拥塞控制机制,通过观察连续的不同长度的数据包的RTT的变化来确定网络带宽和适宜的拥塞窗口。实验结果证明,这种新机制在吞吐量、公平性、友好性方面均好于当前主流的端到端拥塞控制机制。     

一种接收方驱动的无线TCP拥塞控制机制

为了提高有线/无线异构网络中TCP的传输性能,提出了一种新的接收方驱动的TCP拥塞控制机制TCP_LEB.该机制在接收方计算当前带宽和往返时间(RTT),并根据以往的带宽推导以后的可用带宽,然后反馈到发送方作为发送依据.同其他类似研究相比,该方法明显提高了无线网络中TCP的性能.仿真实验结果验证了算法的良好效果.     

无线网络中一种智能控制的组播拥塞控制机制

针对现有组播拥塞控制算法应用到无线网络中存在的性能下降问题,提出一种基于新的智能组播拥塞控制机制ECMCC。ECMCC机制根据网络相对队列时延和数据包丢失检测网络的拥塞状态,采用代表集合机制反馈信息,利用专家控制器的推理判断区分丢包原因和当前的网络状态,进而采取不同的控制策略调节组播源端发送速率。仿真结果表明,ECMCC机制收敛速度快、灵敏性好、速率变化平滑,在有线网络中具有良好的TCP友好性。同时,ECMCC能有效区分网络拥塞和随机差错,提高了网络的吞吐量,适用于无线网络环境,且在无线网络较低误码率时具有一定的TCP友好性。     

一种路由器辅助的多速率组播拥塞控制策略

IP组播是一种有效的数据传输方式,由于其自身特性决定了在组播中实现可靠性和拥塞控制非常困难,因此设计合适的拥塞控制协议是一个迫切需要解决的问题,而这一点仅依赖于端系统控制拥塞的能力是有限的,文中尝试将一种主动队列管理(AQM)算法REM加入到多速率组播拥塞控制协议RLC当中,使网络本身参与对拥塞的监测和预防,并通过利用REM提供的拥塞指示(CI)对现有多速率组播解决办法在接收者加入层或者离开层的行为策略上进行改进。     

一种改进的多速率组播拥塞控制协议DAMCC

提出了一种新的动态分配带宽的多速率组播拥塞控制策略(DAMCC).针对当前使用的多速率组播拥塞控制策略RLC调整速率粒度粗糙、接收端带宽的利用不充分的问题,DAMCC设计了动态分段计算增强层的速率算法.执行DAMCC的接收端,根据反馈的响应信息计算网络往返延迟(RTT),进而计算自身的TCP友好速率,以相应的速率接收组播数据,达到与TCP流公平竞争网络资源的目的.仿真实验表明,该拥塞控制策略比分层组播控制常用的典型策略(RLC)更有效地利用网络带宽,解决网络带宽的异构性问题,并能通过接收端计算TCP友好速率,使接收端达到与TCP流公平竞争网络资源的目的.     

基于种群生态的组播拥塞控制机制

针对现有TCP类组播拥塞控制机制不具有速率平滑性、往返时间(RTT)公平性以及在高速环境中传输效率低的问题,提出一种基于种群生态理论的自适应高速组播拥塞控制机制。该机制在每个接收端实现瓶颈链路带宽和背景流速率的测量,并将这两个测量值用于种群生态模型中以计算期望服务速率,然后使用一种简单的反馈抑制机制选取期望服务速率最小的接收端作为代表,该代表将其期望服务速率反馈给源端控制发送速率。仿真结果表明新机制发送速率平滑,具有RTT公平性,在低速网络和高速网络中都能与单播流公平共享带宽资源。     

一种自适应比例系数的TCP拥塞控制策略

互联网业务的快速发展使得网络拥塞日益严重,因此如何减轻网络拥塞也就成为当前研究的热点。针对这一问题,首先叙述了TCP拥塞控制的基本原理及其相关算法;然后对拥塞控制算法进行了详细分析并提出了自适应比例系数的新策略;最后对新策略进行NS2仿真。仿真结果表明,新方法提高了包投递率,降低了端到端时延。     

Enabling network calculus-based simulation for TCP congestion control

In this paper, we propose to speed up the simulation performance for TCP-operated networks by incorporating network calculus-based models in a simulation framework. In the simulation framework, we describes the operational properties of TCP congestion control, additive increase and multiplicative decrease (AIMD) and slow start, together with the queue discipline in the domain of network calculus. In order to determine network calculus models for TCP congestion, we first devise a simple TCP throughput model which approximately determines the range of per-flow throughput that one TCP can attain in a given interval, given the number of packet losses in the interval. We then exploit the TCP model to define a collection of network calculus theorems that regulate TCP flows in the range between the upper- and lower-limits on the TCP per-flow throughput in the corresponding interval. Finally, we incorporate the derived rules (theorems) into ns-2 to obtain a network calculus-based (NC-based) simulation, and carry out both the NC-based and the packet-level simulation to evaluate the performance gain and accuracy of the NC-based simulation, where the former is represented in perspective of the execution time (wall time) incurred in conducting the simulations and the later is evaluated in terms of the difference between results obtained in both the packet-level and NC-based simulation. The simulation results indicate that an order of magnitude or more (maximally 30 times) improvement in the execution time is achieved and the performance improvement becomes more salient as the network size increases in perspective of network-link capacities and the number of flows. The discrepancy observed between the NC-based simulation and the packet-level simulation, on the other hand, is minimally 1–2% and maximally 8–12% in a wide spectrum of network topologies and traffic loads. Additionally the results also indicate that the NC-based simulation outperforms a fluid-model-based simulation realized with the use of the time-stepped hybrid simulation technique, and that the performance improvement of the NC-based simulation is still held in IEEE 802.11-based wireless networks and also immune to the type of the simulation platform consisting of ns-2, operating system, and hardware specification.     

Linux中传输控制协议的拥塞控制分析

TCP(transportcontrolprotocol)的性能在很大程度上取决于其所使用的拥塞控制算法。传统的TCP在实现多种拥塞控制算法集成的过程中会出现种种问题。LinuxTCP可以实现多种拥塞控制算法的优化集成,本文分析了linuxTCP的独特实现方法,并将其与传统实现和IETF规范作了相应比较。