基于拥塞估计的TCP窗口在线学习方法

针对传统TCP拥塞窗口更新、控制机制所导致的Ad Hoc网络吞吐量下降的问题,利用机器学习算法来改善TCP在Ad Hoc网络中的性能。该方法利用确认帧的时间间隔,通过连续动作集(CALA)算法快速学习并估计当前网络链路中的拥塞状况,从而能够迅速调整TCP拥塞窗口。仿真实验表明:当Ad Hoc网络环境较好时,学习型TCP的吞吐量略优于TCP-Few、TCP-Reno协议,但在环境较差的情况下,学习型TCP的吞吐量远远优于TCP-Few和TCP-Reno协议。     

一种改进的TCP over OBS网络拥塞控制策略

首先深入分析了TCP over OBS网络中造成TCP性能下降的各种原因.在此基础上,考虑将近年来提出的GAIMD算法与OBS网络的特点相结合,提出了一种改进的拥塞控制策略.该策略能在一定程度上改善OBS网络由于随机竞争丢包给TCP性能带来的负面影响.     

MP-Start：基于带宽测量的分阶段TCP慢启动机制

针对TCP慢启动机制门限值参数难于设置以及突发流量引起网络抖动的问题，提出了一种基于带宽测量及分阶段实施的TCP慢启动改进算法。该方法利用在线网络带宽测量技术，探测出网络带宽，从而根据网络状态的动态变化实现慢启动门限值的动态更新，同时，采用分阶段方法调节拥塞窗口的增加，在拥塞窗口大于门限值一半时，拥塞窗口增幅为门限值和拥塞窗口差值的一半，逐步迭代逼近门限值，使拥塞窗口在连接启动和过渡到拥塞避免阶段增加幅度比较小，而在中间阶段窗口增加幅度比较大。有效避免了多个分组丢失现象的发生，实现了连接的平滑接入和过渡到拥塞避免阶段；为提高改进算法的性能，设计了一种灵活的参数化的模型和自适应参数设置方案。大量仿真实验结果表明MP-Start能在多种网络环境下有效改善网络性能，如降低分组丢弃数、减少数据传输时间、降低共享链路分组队列长度、保持连接的传输平滑性。     

IP网络中TCP拥塞控制协议的稳定性分析

文章用泛函微分方程建立了TCP拥塞控制协议的动态模型,通过该模型分析了当前Internet上使用的TCP拥塞控制算法,导出了稳定性条件,结果表明该算法在一定网络环境下是不稳定的.     

基于ECN跨层机制的无线TCP性能改进方案

针对无线环境下TCP（传输控制协议）调用拥塞控制算法致使性能下降的问题,提出一种基于ECN（显式拥塞通知）跨层机制的无线TCP改进方法。算法在ECN机制上判断网络是否拥塞以及丢包发生时具体丢包类型。并在此基础上针对网络具体状况采取不同的拥塞窗口控制机制,更精确的网络信息有效提高了数据发送的可靠性。仿真结果表明该算法可提...     

吉比特网络CUBIC拥塞控制算法仿真研究

分析了TCP RENO的不足,比较了BIC算法和CUBIC算法,采用响应函数理论比较了三种TCP算法.在吉比特网络环境下对CUBIC算法进行了仿真.仿真研究表明,CUBIC算法能在高速网络环境中有效的提升网络速度,在拥塞丢包严重,网络流量很低时快速恢复网络速度;同时因为拥塞窗口波动太大,高速TCP流的吞吐量变化太大,带宽的利用率很不稳定.     

卫星网中基于时间戳的TCP拥塞控制算法研究

TCP(传输控制协议)拥塞控制机制直接使用在卫星网中存在很多不足。针对卫星网通信时延长、网络环境变化复杂的特点，利用TCP协议中的时间戳扩展选项，设计实现了一种改进的TCP重传和拥塞控制算法，能够根据RTr(Round Trip Time，往返时间)的变化对网络情况进行预测，从而及时重传数据包并调整窗口大小，仿真实验证明改进算法能够很好地提高TCP性能。     

一种基于带宽估计的战术互联网TCP改进机制

无线的战术互联网通常面临复杂的电磁环境,高误码率、终端的频繁移动等恶劣的通信环境使得针对有线网络设计的TCP协议传榆性能急剧下降.针对战术互联网提出了一种基于带宽估计的TCP改进机制,该机制利用TCP确认帧携带的数据包到达时间来估算带宽,并用动态的低通滤波器来平滑带宽的估计值.在此基础上用带宽的估计值更新拥塞窗口,避免在发生链路错误时启动拥塞控制机制,由此提高TCP在战术互联网中的性能.实验结果表明,该算法能减少链路差错对TCP性能带来的影响,提高TCP在战术互联网上的传输性能.     

TCP拥塞控制研究综述

系统深入地研究了TCP协议中的拥塞控制机制,TCP改进协议中研究最多的就是对TCP拥塞窗口调节机制的改进.从这个方面来看主要可以分为三种改进类型,即基于分组丢弃反馈的拥塞窗口调节方式;基于路径延时反馈的拥塞窗口调节方式;基于显式反馈和带宽测量的拥塞窗口调节方式.另外还针对无线网络的固有特性讨论了无线网络上TCP协议的一些改进方案.深入地分析了一些典型的算法,对它们的优劣做了详细的分析和总结,并提出了今后的一些研究方向.     

卫星TCP/ATM传输中的明确窗口指示拥塞控制策略研究

卫星ATM是近年来卫星通信领域的一个研究热点,TCP业务在卫星ATM中的传输是其中一个重要的研究课题.由于在TCP协议中主要是通过对窗口的控制来实现拥塞控制,而卫星信道传输的长延时特性大大降低了TCP层拥塞控制的效率.本文提出一种基于UBR传输的明确窗口指示拥塞控制策略,仿真结果表明在效率、公平性、VBR背景传输下的性能等各方面,取得了比目前广泛使用的Reno TCP更好的结果.并且该算法实现简单,交换机实现零信元丢失的缓冲区很小并且与TCP源连接的数目无关.     

一种基于ECN的无线TCP拥塞控制机制

针对无线异构链路环境中传统TCP拥塞控制机制效率较低的问题,本文提出一种基于ECN的多级反馈算法。该算法在ECN的基础上可以根据RTT动态地给网络划分等级并进行概率反馈,改变了ECN的二元特性,有效提高了无线数据传输效率。仿真结果表明该算法可降低丢包率,减少拥塞次数,提高吞吐量。     

TCP Westwood: End-to-End Congestion Control for Wired/Wireless Networks

TCP Westwood (TCPW) is a sender-side modification of the TCP congestion window algorithm that improves upon the performance of TCP Reno in wired as well as wireless networks. The improvement is most significant in wireless networks with lossy links. In fact, TCPW performance is not very sensitive to random errors, while TCP Reno is equally sensitive to random loss and congestion loss and cannot discriminate between them. Hence, the tendency of TCP Reno to overreact to errors. An important distinguishing feature of TCP Westwood with respect to previous wireless TCP extensions is that it does not require inspection and/or interception of TCP packets at intermediate (proxy) nodes. Rather, TCPW fully complies with the end-to-end TCP design principle. The key innovative idea is to continuously measure at the TCP sender side the bandwidth used by the connection via monitoring the rate of returning ACKs. The estimate is then used to compute congestion window and slow start threshold after a congestion episode, that is, after three duplicate acknowledgments or after a timeout. The rationale of this strategy is simple: in contrast with TCP Reno which blindly halves the congestion window after three duplicate ACKs, TCP Westwood attempts to select a slow start threshold and a congestion window which are consistent with the effective bandwidth used at the time congestion is experienced. We call this mechanism faster recovery. The proposed mechanism is particularly effective over wireless links where sporadic losses due to radio channel problems are often misinterpreted as a symptom of congestion by current TCP schemes and thus lead to an unnecessary window reduction. Experimental studies reveal improvements in throughput performance, as well as in fairness. In addition, friendliness with TCP Reno was observed in a set of experiments showing that TCP Reno connections are not starved by TCPW connections. Most importantly, TCPW is extremely effective in mixed wired and wireless networks where throughput improvements of up to 550% are observed. Finally, TCPW performs almost as well as localized link layer approaches such as the popular Snoop scheme, without incurring the overhead of a specialized link layer protocol.     

即时恢复--一种新的TCP拥塞控制快速恢复算法

针对TCP连接的网络传输中经常会出现同一窗口多个分组丢失的情况,本文提出了一种新的TCP拥塞控制快速恢复算法:即时恢复算法。即时恢复算法能在恢复阶段探测网络的可用带宽,并将之用于窗口拥塞控制。另外,通过动态设定退出恢复阶段的参数域值,除了能恢复首次丢失的多个分组外,该算法还能很好的解决恢复阶段分组进一步丢失的情况。与SACK、FACK TCP等算法需要对TCP协议的发送、接收部分同时修改不同,该算法只需修改协议的发送部分,而接收部分不需作任何改变。在ns仿真环境的仿真结果表明:在同一窗口有多个分组丢失时,即时恢复算法的性能比TCP New-Reno有较大提高,与 SACK TCP性能相当。     

基于TCP/IP的卫星通信传输链路的改进

卫星网络固有的一些特性影响了TCP／IP的性能。针对延迟、拥塞率、比特差错率、网络不对称性等问题,提出了支持较大的流量控制窗口及改进拥塞控制算法的方法,对现有的TCP／IP进行了改进。     

无线网络中TCP拥塞控制算法的性能分析

根据无线网络中存在随机数据包丢失的特定情况,对TCP拥塞控制算法在无线网络中的性能进行了分析。理论分析和仿真结果表明,随着无线链路中随机数据包丢失概率的增加,TCP拥塞控制算法将导致无线网络性能的严重下降。     

对半增长TCP拥塞控制算法研究

首先简要介绍了TCP(Transmission Control Protocol)Reno拥塞控制算法,在此基础上分析了对半增长TCP(Binary Increase TCP,BI-TCP)拥塞控制算法的优点及其不足,并提出改进算法———BIplus算法,最后使用NS2(Network Simulator Version2.26)仿真来验证提出的改进算法。     

A study of deploying smooth‐ and responsive‐TCPs with different queue management schemes

While there exist extensive research works on congestion control and active queue management, or the joint dynamics of a congestion control strategy with the random early detection (RED) algorithm, little has been done on the interactions between different window adjustment strategies and different queue management schemes such as DropTail and RED. In this paper, we consider a spectrum of TCP‐friendly additive increase and multiplicative decrease (AIMD) parameters. At the one end of this spectrum, smooth‐TCP enhances smoothness for multimedia applications by reducing the window decrease ratio upon congestion, at the cost of the additive increase speed and the responsiveness to available bandwidth. At the other end, responsive‐TCP enhances the responsiveness by increasing the additive increase speed, at the cost of smoothness. We investigate the network dynamics with various combinations of AIMD parameters and queue management schemes, under different metrics. The investigation is conducted from the deployment (especially incremental deployment) point of view. We discussed the impact of the interactions on the goodput, fairness, end‐to‐end delay, and its implications to energy consumption on mobile hosts. Copyright © 2008 John Wiley & Sons, Ltd.     

一种支持分级服务和最小带宽保证的改进TCP算法

本文提出了一种支持分级服务和最小带宽保证的改进TCP算法－DSAS－TCP，通过对TCP算中慢启动阈值和最小拥塞窗口的分级设置来使不同等级连接的平均吞吐量产生分级，并保证用户的最小带宽需求。通过理论分析和仿真实验验证了该算法的有效性。     

Improving fairness of PGMCC

PGM congestion control (pgmcc), a single‐rate multicast congestion control scheme, is one of the most promising schemes which aim to solve the problem of multicast fairness with TCP. However, by deep investigation, we find that there exist two inappropriate mechanisms in this scheme, which are the fixed slow start threshold (ssthresh) and the mechanism of changing a group representative (acker). Our experiments have revealed the fact that these mechanisms can lead to the unfairness of pgmcc under some network conditions. In this paper, two new mechanisms have been proposed to replace the original ones. One mechanism is to make the sender adapt the value of ssthresh to the network conditions to mimic the action of TCP, and in order to avoid being more aggressive than TCP, the other one is to make the sender reduce the congestion window by half when the acker changes. Our experiment results, parts of which are discussed in this paper, show that the modified pgmcc can achieve better performance than the original one. Copyright © 2005 John Wiley & Sons, Ltd.