PSTCP：小缓存高速网络拥塞控制算法

针对当前网络拥塞控制算法在极小缓存高速网络中带宽利用率差的问题,研究了TCP机制本身造成的突发流量现象,提出一种新的拥塞控制算法——PSTCP。在整个网络连接过程中,该算法采用“隔开”平滑发送的思想;在网络拥塞发生时,采用公平因子c和减少因子decrement对窗口进行实时微调。实验表明,PSTCP在小缓存区、高带宽网络环境下,保障了高的带宽利用率,有好的收敛性和公平性。     

小缓存高速网络的拥塞控制算法

传统高带宽拥塞控制算法不适用于小缓存高速网络。针对该问题提出端算法与中间节点结合的拥塞控制算法,根据缓存区占用大小调整调节因子a、保障因子c,自适应增加或减少窗口大小。实验结果表明,该算法可以在小缓存高速网络中实现高带宽利用率、快速收敛和不同RTT流的公平性。     

改进的网络拥塞控制策略算法研究

研究网络拥塞优化控制问题.针对网络承载量的不断增加,使得网络传输效率降低.传统网络拥塞控制算法要求系统根据无线网络的容量实时编号,动态调整TCP拥塞窗口的大小,难于建立准确的数学模型,从而导致网络带宽利用率低,网络拥塞严重.为了降低网络拥塞的概率,提出了一种改进的无线TCP拥塞控制算法.算法主要是集中解决在TCP拥塞窗口的大小调整问题上,首先利用BP神经网络对参数进行训练,有效地解决了TCP拥塞窗口大小的调整,从而实现了拥塞避免、快速重传和快速恢复机制,改善网络性能.实验结果表明改进的算法提高了网络平均吞吐量,带宽利用率更高,有效避免了网络拥塞.     

基于动态带宽估计的TCP Vegas改进算法

结合Gallop-Vegas和TCP Vegas-A等算法的优点,并在其基础上做了进一步的改进,提出基于动态带宽估计的TCP Vegas 改进算法.该算法实现在慢启动和拥塞避免两个阶段动态地估计网络实际带宽的利用率情况,并采取相应的拥塞控制策略.经仿真实验证明,该算法对TCP Vegas会出现因拥塞窗口爆发性增长而使得慢启动过早结束、在拥塞避免阶段非对称网络中的反向拥塞导致的吞吐量骤降,以及在与TCP Reno共存时的兼容性差等问题有良好的改进.     

基于带宽估计和ECN的无线TCP改进

针对无线环境下TCP调用拥塞控制算法致使性能下降的问题,提出一种基于带宽估计和显式拥塞通知的无线TCP改进方法。在数据发送端采用带宽估计算法优化拥塞窗口尺寸,与具有显式拥塞通知的路由器配合区分分组丢失性质,利用选择性确认选项,加快单窗口多包丢失时拥塞窗口恢复速度。仿真结果表明,改进后的TCP吞吐量超过TCP_SACK近30%,超过TCP_Reno近52%。     

基于改进慢启动算法的大文件快速传输

针对传统TCP在当前网络环境下传输大文件性能较低的问题,对TCP传输协议中的慢启动算法部分进行了相应的研究与优化。根据标准慢启动算法存在的问题并结合高速网络以及大文件传输的性能特点,提出了一个具有网络状态感知能力的慢启动改进算法。改进算法主要优化了TCP拥塞窗口的增长策略,它实时地监测文件在传输过程中TCP报文段的往返时间（RTT）,并根据RTT的变化情况采用不同的窗口增长方式更新拥塞窗口;将改进算法部署在Linux网络模块中并分别在模拟网络环境和实际网络中进行测试。实验结果显示,改进算法能使发送窗口一直保持在一个较高的水平,实际数据传输速率和吞吐量均有了明显的提高。     

EHSTCP:改进的高速TCP算法

TCP在高带宽时延积网络中不能获得良好的性能,主要表现为低的吞吐量和大的窗口震荡.HSTCP算法解决了传统TCP算法在高带宽时延积网络下的性能瓶颈,但HSTCP在拥塞点时会产生大量的数据包丢失,同时当队列管理为去尾算法时,存在着严重的RTT不公平性问题.针对HSTCP算法的性能缺陷,该文提出一种在拥塞避免阶段进行拥塞避免模式切换的改进算法,称为EHSTCP.基于拥塞窗口历史值的端到端可用带宽预测方法,利用拥塞窗口历史信息来判断拥塞避免切换点.同时引入RTT公平因子,消除了HSTCP的RTT不公平性问题.NS2仿真实验验证了算法的有效性.     

高速网络中TCP拥塞控制研究综述

通过分析现行TCP算法在高速网络中的局限性,介绍几种最新的高速网络拥塞控制算法:BIC TCP、FASTTCP、STCP、HTCP和HSTCP.从带宽利用率、公平性和友好性方面对上述算法进行分析和比较,指出算法存在的不足,提出研究方向.     

带宽保证环境下TCP算法改进及其模型分析

基于差分服务模型的带宽保证服务已经得到较多的应用，这类通过分组标记和丢弃算法实现的非刚性带宽保证具有实现简单、扩展性强的特点。但是，由于端系统的TCP协议对合约带宽信息的不感知，使得应用难以获得网络提供的带宽保证。在分析了双窗口TCP拥塞控制算法的基础上，提出了基于合约窗口的拥塞控制算法，并对算法进行了测试和建模分析。该算法简单、易于实现。并且在网络突发拥塞时，收敛速度快，不影响网络的稳定性。     

高带宽延时网络下拥塞控制协议比较与分析

随着网络技术的飞速发展和接入性能的不断提高,如今全世界的互联主干网络呈现出一种高带宽高延时(High Bandwidth-Delay Product Networks)的网络特性.在这种网络特性下,传统网络中的TCP拥塞控制协议已经开始显现出不适应性,如带宽利用率低下、流量抖动频繁等问题.近些年来,各国学者均提出一些适应这种网络环境变化的拥塞控制协议,基于这些协议中窗口调节机制所采用的反馈信息,本文将其划分为三类:基于丢包反馈的协议、基于路径延时反馈的协议和基于显式反馈的协议,并分析了这些协议的优缺点.在总结了高带宽延时网络下拥塞控制协议研究成果的基础上,进一步分析了网络中的传输延时RTT、瓶颈路由器缓存和路由器队列管理算法对现有拥塞控制协议的影响,并通过NS2对各协议在高带宽延时网络下的性能进行了一次全面的比较和评价.最后文章在总结前人工作的基础上,指出了高带宽延时网络下拥塞控制协议性能优化的研究方向.     

S-shaped TCP: A transport protocol for improving the performance of TCP in fast long-distance networks

It is well known that TCP does not fully utilize the available bandwidth in fast long-distance networks. This paper proposes S-shaped TCP (SS-TCP). The window growth function of SS-TCP is, in the steady state condition, S-shaped, and it can be divided into three regions. In region I, the window growth rate of SS-TCP is the same as that of standard TCP (STD-TCP). In region II, the window of SS-TCP grows faster than that of STD-TCP. In region III, SS-TCP decreases its window growth rate as the network is becoming congested. This paper also proposes SS-TCPW, an enhanced version of SS-TCP. It makes an end-to-end estimation of the available bandwidth as TCP Westwood+. Based on the estimation, SS-TCPW determines the boundary of region III, and decreases its window size. We evaluate the performance of SS-TCP and SS-TCPW in terms of the metrics that are important for high speed transport protocols; buffer requirement, TCP friendliness, RTT fairness and convergence time. The results showed that SS-TCP has much better performance than HighSpeed TCP (HS-TCP) in terms of buffer requirement and RTT fairness. SS-TCPW has better performance than HS-TCP and SS-TCP in all metrics. The results also clarified that SS-TCP and SS-TCPW have much better TCP friendliness than FAST-TCP.     

Time-averaging of high-speed data transfer protocols

We propose two modeling approaches of additive-increase/multiplicative-decrease (AIMD) congestion control mechanisms. The first separates the increase and decrease parts whereas the second describes the rate evolution of the congestion window as a continuous process governed by a differential equation. We relate these approaches and show that the second (fluid-flow) model results from deterministic time averaging of the first (discontinuous) model. A generalized class of nonlinear protocols, which includes Floyd's HighSpeed TCP, is then proposed and analyzed. Our findings are validated by simulation.     

Analysis of MIMD congestion control algorithm for high speed networks

Proposals to improve the performance of TCP in high speed networks have been recently put forward. Examples of such proposals include High Speed TCP, Scalable TCP, and FAST. In contrast to the additive increase multiplicative decrease algorithm used in the standard TCP, Scalable TCP uses a multiplicative increase multiplicative decrease (MIMD) algorithm for the window size evolution. In this paper, we present a mathematical analysis of the MIMD congestion control algorithm in the presence of random losses. Random losses are typical to wireless networks but can also be used to model losses in wireline networks with a high bandwidth-delay product. Our approach is based on showing that the logarithm of the window size evolution has the same behaviour as the workload process in a standard G/G/1 queue. The Laplace–Stieltjes transform of the equivalent queue is then shown to directly provide the throughput of the congestion control algorithm and the higher moments of the window size. Using ns-2 simulations, we validate our findings using Scalable TCP.     

TCP-BM:一种适用于异构网络的TCP协议改进策略

针对异构网络中的拥塞控制问题进行了研究,以传统的TCP Reno协议为基础提出一种改进算法TCP-BM。利用往返时延值将慢启动阶段分为三个部分;利用往返时延值将拥塞避免阶段分为正增长和负增长两个过程。网络发生丢包后,通过往返时延值与历史记录的比较以及估计的带宽值的比较,区分丢包原因,从而对拥塞窗口和慢启动阈值采取不同调整策略。仿真验证证明,改进后的TCP算法性能优于传统的TCP Reno协议。     

RED算法的数学模型研究

RED算法能够及时预测网络拥塞的到来,并同过标记避免网络拥塞,同时还解决了TCP全局同步的问题.RED算法对参数过于敏感一直是研究的主要问题.建立RED算法的数学模型,从数学角度分析RED算法的原理以及工作过程.对数学模型的静态分析、参数分析研究各个参数在算法中所起的作用以及其影响因子;给出如何设定参数才能使RED算法达到更好的性能.     

LIAD: Adaptive bandwidth prediction based Logarithmic Increase Adaptive Decrease for TCP congestion control in heterogeneous wireless networks

For accessing plentiful resources in the Internet through wireless mobile hosts, diverse wireless network standards and technologies have been developed and progressed significantly. The most successful examples include IEEE 802.11 WiFi for wireless networks and 3G/HSDPA/HSUPA for cellular communications. All IP-based applications are the primary motivations to make these networks successful. In TCP/IP transmissions, the TCP congestion control operates well in the wired network, but it is difficult to determine an accurate congestion window in a heterogeneous wireless network that consists of the wired Internet and various types of wireless networks. The primary reason is that TCP connections are impacted by not only networks congestion but also error wireless links. This paper thus proposes a novel adaptive window congestion control (namely Logarithmic Increase Adaptive Decrease, LIAD) for TCP connections in heterogeneous wireless networks. The proposed RTT-based LIAD has the capability to increase throughput while achieving competitive fairness among connections with the same TCP congestion mechanism and supporting friendliness among connections with different TCP congestion control mechanisms. In the Congestion Avoidance (CA) phase, an optimal shrink factor is first proposed for Adaptive Decreasing cwnd rather than a static decreasing mechanism used by most approaches. Second, we adopt a Logarithmic Increase algorithm to increase cwnd while receiving each ACK after causing three duplicate ACKs. The analyses of congestion window and throughput under different packet loss rate are analyzed. Furthermore, the state transition diagram of LIAD is detailed. Numerical results demonstrate that the proposed LIAD outperforms other approaches in goodput, fairness, and friendliness under diverse heterogeneous wireless topologies. Especially, in the case of 10% packet loss rate in wireless links, the proposed approach increases goodput up to 156% and 1136% as compared with LogWestwood+ and NewReno, respectively.     

Achieving high throughput and TCP Reno fairness in delay-based TCP over large networks

The transport control protocol (TCP) has been widely used in wired and wireless Internet applications such as FTP, email and http. Numerous congestion avoidance algorithms have been proposed to improve the performance of TCP in various scenarios, especially for high speed and wireless networks. Although different algorithms may achieve different performance improvements under different network conditions, designing a congestion algorithm that can perform well across a wide spectrum of network conditions remains a great challenge. Delay-based TCP has a potential to overcome above challenges. However, the unfairness problem of delay-based TCP with TCP Reno blocks widely the deployment of delay-based TCP over wide area networks. In this paper, we proposed a novel delay-based congestion control algorithm, named FAST-FIT, which could perform gracefully in both ultra high speed networks and wide area networks, as well as keep graceful fairness with widely deployed TCP Reno hosts. FAST-FIT uses queuing delay as a primary input for controlling TCP congestion window. Packet loss is used as a secondary signal to adaptively adjust parameters of primary control process. Theoretical analysis and experimental results show that the performance of the algorithm is significantly improved as compared to other state-of-the-art algorithms, while maintaining good fairness.     

窗口限制系统中基于令牌的Fast-TCP的延时性能分析

给出了在高带宽时延乘积网络中无拥塞丢包的TCP缓冲区的占用量的微分方程,然后针对广域网中窗口大小小于网络带宽时延乘积和无线网络中,由于误码丢包而使窗口尺寸无法达到链路带宽时延乘积(如卫星网)的情况,分析了一种基于令牌的Fast-TCP机制,得出基于令牌的ACK延时机制,不仅能够大大减少缓冲区的占用量结论,而且可获得与TCP在无限缓冲区下的同样的吞吐量.还把这个结论推广到多连接的情况,在以前论文中没有涉及.