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     

EVA: a better TCP version for resource‐insufficient networks

TCP Vegas exhibits unfair congestion avoidance mechanism, which aggravates when there are insufficient network resources to accommodate buffer space of a pipe (bandwidth delay product). To remedy this shortcoming, we propose an Enhanced VegAs (EVA) that employs three auxiliary mechanisms: Δ revision, congestion detection and congestion tendency detection. A 2^k factorial design with replications is used to study the effect of the three mechanisms. Our results show that TCP EVA achieves better performance than Vegas under various network conditions. Furthermore, congestion avoidance schemes, such as TCP EVA, perform much better than congestion control schemes, such as TCP Reno, in resource‐insufficient networks. Copyright © 2002 John Wiley & Sons, Ltd.     

ACC: using active networking to enhance feedback congestion controlmechanisms

Active congestion control (ACC) uses active networking (AN) technology to make feedback congestion control more responsive to network congestion. Current end-to-end feedback congestion control systems detect and relieve congestion only at endpoints. ACC includes programs in each data packet that tell routers how to react to congestion without incurring the round-trip delay that reduces feedback effectiveness in wide area networks. The congested router also sends the new state of the congestion control algorithm to the endpoints to ensure that the distributed state becomes consistent. We present a model for extending feedback congestion control into an active network, apply that model to TCP congestion control, and present simulations that show that the resulting system exhibits up to 18 percent better throughput than TCP under bursty traffic. In simulations without bursty traffic, the systems behaved comparably     

An enhanced congestion avoidance mechanism for TCP Vegas

TCP Vegas detects network congestion in the early stage and successfully prevents periodic packet loss that usually occurs in traditional schemes. It has been demonstrated that TCP Vegas achieves much higher throughput than TCP Reno. However, TCP Vegas cannot prevent unnecessary throughput degradation when congestion occurs in the backward path. In this letter, we propose an enhanced congestion avoidance mechanism for TCP Vegas. By distinguishing whether congestion occurs in the forward path or not, it significantly improves the connection throughput when the backward path is congested.     

TCP-Jersey for wireless IP communications

Improving the performance of the transmission control protocol (TCP) in wireless Internet protocol (IP) communications has been an active research area. The performance degradation of TCP in wireless and wired-wireless hybrid networks is mainly due to its lack of the ability to differentiate the packet losses caused by network congestions from the losses caused by wireless link errors. In this paper, we propose a new TCP scheme, called TCP-Jersey, which is capable of distinguishing the wireless packet losses from the congestion packet losses, and reacting accordingly. TCP-Jersey consists of two key components, the available bandwidth estimation (ABE) algorithm and the congestion warning (CW) router configuration. ABE is a TCP sender side addition that continuously estimates the bandwidth available to the connection and guides the sender to adjust its transmission rate when the network becomes congested. CW is a configuration of network routers such that routers alert end stations by marking all packets when there is a sign of an incipient congestion. The marking of packets by the CW configured routers helps the sender of the TCP connection to effectively differentiate packet losses caused by network congestion from those caused by wireless link errors. This paper describes the design of TCP-Jersey, and presents results from experiments using the NS-2 network simulator. Results from simulations show that in a congestion free network with 1% of random wireless packet loss rate, TCP-Jersey achieves 17% and 85% improvements in goodput over TCP-Westwood and TCP-Reno, respectively; in a congested network where TCP flow competes with VoIP flows, with 1% of random wireless packet loss rate, TCP-Jersey achieves 9% and 76% improvements in goodput over TCP-Westwood and TCP-Reno, respectively. Our experiments of multiple TCP flows show that TCP-Jersey maintains the fair and friendly behavior with respect to other TCP flows.     

大带宽时延积网络TCP Vegas自适应慢启动算法

TCP Vegas具有比TCP Reno更好的带宽利用能力和稳定性,但是在带宽时延积较大的网络中,TCP Vegas会出现慢启动过早结束、拥塞窗口过小的问题,降低了传输效率.文中在分析慢启动结束的原因和条件的基础上,提出一种对临时性排队时延进行估计,将其排除后再进行慢启动结束条件判断的TCP Vegas慢启动算法,对不同网络条件有自适应能力.仿真结果表明本算法能有效避免慢启动过早结束,使TCP性能明显改善.     

Modeling and Analysis of Active Queue Management Schemes under Bursty Traffic

Traffic congestion arising from the shared nature of uplink channels in wireless networks can cause serious problems for the provision of QoS to various services. One approach to overcome these problems is to implement some effective congestion control mechanisms at the downlink buffer at the mobile network link layer or at gateways on the behalf of wireless network access points. Active queue management (AQM) is an effective mechanism to support end-to-end traffic congestion control in modern high-speed networks. Initially developed for Internet routers, AQM is now being also considered as an effective congestion control mechanism to enhance TCP performance over 3G links. This paper proposes an analytical performance model for AQM using various dropping functions. The selection of different dropping functions and threshold values required for this scheme plays a critical role on its effectiveness. The model uses a well-known Markov-modulated Poisson process (MMPP) to capture traffic burstiness and correlations. The validity of the model has been demonstrated through simulation experiments. Extensive analytical results have indicated that exponential dropping function is a good choice for AQM to support efficient congestion control.     

Vegas plus: improving the service fairness

TCP Vegas is a congestion avoidance scheme designed to prevent the periodic packet loss which occurs in traditional schemes. Since Vegas successfully avoids such packet loss, it achieves much higher throughput than TCP Reno. However, it does not concern the fairness among source-destination pairs with different round-trip times (RTTs). We propose a different mechanism to adjust the window size, this allows TCP to provide much better fairness regardless the large variation of RTTs     

一种改善TCP性能的链路层重传方案

有线网络中TCP拥塞控制机制是建立在网络丢包的基础之上的,所以该机制不能适应无线网络中高误码率造成的无线链路丢包的情况。无线链路层重传技术是改善网络性能因无线信道误码率较高而下降的一项重要措施。文中研究了WCDMA无线网络中链路层重传技术对无线TCP数据传输的影响,比较两种重传方案,通过OPNET仿真技术对其进行仿真比较,得出其中一种更有效的改善TCP传输性能的方案。     

TCP over optical burst-switched networks with controlled burst retransmission

For optical burst-switched (OBS) networks in which TCP is implemented at a higher layer, the loss of bursts can lead to serious degradation of TCP performance. Due to the bufferless nature of OBS, random burst losses may occur, even at low traffic loads. Consequently, these random burst losses may be mistakenly interpreted by the TCP layer as congestion in the network. The TCP sender will then trigger congestion control mechanisms, thereby reducing TCP throughput unnecessarily. In this paper, we introduce a controlled retransmission scheme in which the bursts lost due to contention in the OBS network are retransmitted at the OBS layer. The OBS retransmission scheme can reduce the burst loss probability in the OBS core network. Also, the OBS retransmission scheme can reduce the probability that the TCP layer falsely detects congestion, thereby improving the TCP throughput. We develop an analytical model for evaluating the burst loss probability in an OBS network that uses a retransmission scheme, and we also analyze TCP throughput when the OBS layer implements burst retransmission. We develop a simulation model to validate the analytical results. Simulation and analytical results show that an OBS layer with controlled burst retransmission provides up to two to three orders of magnitude improvement in TCP throughput over an OBS layer without burst retransmission. This significant improvement is primarily because the TCP layer triggers fewer time-outs when the OBS retransmission scheme is used.     

Implicit admission control

Internet protocols currently use packet-level mechanisms to detect and react to congestion. Although these controls are essential to ensure fair sharing of the available resource between multiple flows, in some cases they are insufficient to ensure overall network stability. We believe that it is also necessary to take account of higher level concepts, such as connections, flows, and sessions when controlling network congestion. This becomes of increasing importance as more real-time traffic is carried on the Internet, since this traffic is less elastic in nature than traditional Web traffic. We argue that, in order to achieve better utility of the network as a whole, higher level congestion controls are required. By way of example, we present a simple connection admission control (CAC) scheme which can significantly improve the overall performance. This paper discusses our motivation for the use of admission control in the Internet, focusing specifically on control for TCP flows. The technique is not TCP specific, and can be applied to any type of flow in a modern IP infrastructure. Simulation results are used to show that it can drastically improve the performance of TCP over bottleneck links. We go on to describe an implementation of our algorithm for a router running the Linux 2.2.9 operating system. We show that by giving routers at bottlenecks the ability to intelligently deny admission to TCP connections, the goodput of existing connections can be significantly increased. Furthermore, the fairness of the resource allocation achieved by TCP is improved     

A new approach to ensure fairness over the Internet

Congestion signaling is an essential issue for ensuring a high network performance. Explicit congestion notification (ECN) has been proved to provide a faster indication of congestion and thus improve the QoS of a TCP/IP network. In this paper, we present a new scheme for ECN named fair in‐time marking (FIM), which employs a mechanism that as well as providing an indication of incipient congestion, assures a fair service to all the connections. To facilitate such services using FIM, we propose inclusion of some simple yet effective functionalities in the routers. This is important as the client base of the Internet is increasing rapidly and the demand for a reasonably fair service is getting stronger. Experiments show that FIM offers the best fairness, sometimes better by around 20% or more without affecting efficiency, compared with other proposed schemes for ECN. Copyright © 2004 John Wiley & Sons, Ltd.     

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.     

The Impact of Loss Recovery on Congestion Control for Reliable Multicast

Most existing reliable multicast congestion control (RMCC) mechanisms try to emulate TCP congestion control behaviors for achieving TCP-compatibility. However, different loss recovery mechanisms employed in reliable multicast protocols, especially NAK-based retransmission and local loss recovery mechanisms, may lead to different behaviors and performance of congestion control. As a result, reliable multicast flows might be identified and treated as non-TCP-friendly by routers in the network. It is essential to understand those influences and take them into account in the development and deployment of reliable multicast services. In this paper, we study the influences comprehensively through analysis, modelling and simulations. We demonstrate that NAK-based retransmission and/or local loss recovery mechanisms are much more robust and efficient in recovering from single or multiple packet losses within a single round-trip time (RTT). For a better understanding on the impact of loss recovery on RMCC, we derive expressions for steady-state throughput of NAK-based RMCC schemes, which clearly brings out the throughput advantages of NAK-based RMCC over TCP Reno. We also show that timeout effects have little impact on shaping the performance of NAK-based RMCC schemes except for extremely high loss rates (>0.2). Finally, we use simulations to validate our findings and show that local loss recovery may further increase the throughput and deteriorate the fairness properties of NAK-based RMCC schemes. These findings and insights could provide useful recommendations for the design, testing and deployment of reliable multicast protocols and services     

A survey of congestion control schemes for multicast video applications

Congestion control for IP multicast on the Internet has been one of the main issues that challenge a rapid deployment of IP multicast. In this article, we survey and discuss the most important congestion control schemes for multicast video applications on the Internet. We start with a discussion of the different elements of a multicast congestion control architecture. A congestion control scheme for multicast video possesses specific requirements for these elements. These requirements are discussed, along with the evaluation criteria for the performance of multicast video. We categorize the schemes we present into end-to-end schemes and router-supported schemes. We start with the end-to-end category and discuss several examples of both single-rate multicast applications and layered multicast applications. For the router-supported category, we first present single-rate schemes that utilize filtering of multicast packets by the routers. Next we discuss receiver-based layered schemes that rely on routers group?flow control of multicast sessions. We evaluate a number of schemes that belong to each of the two categories.     

A duality model of TCP and queue management algorithms

We propose a duality model of end-to-end congestion control and apply it to understanding the equilibrium properties of TCP and active queue management schemes. The basic idea is to regard source rates as primal variables and congestion measures as dual variables, and congestion control as a distributed primal-dual algorithm over the Internet to maximize aggregate utility subject to capacity constraints. The primal iteration is carried out by TCP algorithms such as Reno or Vegas, and the dual iteration is carried out by queue management algorithms such as DropTail, RED or REM. We present these algorithms and their generalizations, derive their utility functions, and study their interaction.     

TCP/IP网络的动态模型描述

拥塞现象成为TCP/IP网络发展面临的一个重要问题。因此，拥塞控制对TCP/IP网络的鲁棒性和稳定性具有重要作用。目前，网络拥塞控制策略主要包括两类：端到端的控制机制，如TCP拥塞控制算法；网络内部的主动队列管理(AQM)策略。但由于缺乏对网络系统动态特性的了解，这些拥塞控制策略大都基于专家经验，并没有建立完整的理论分析框架。为此，本文从数据流的角度出发，通过建立网络基本单元状态方程模型来实现IP网络系统的数学解析模型，然后用混杂系统来描述TCP带有拥塞控制策略的数据传输过程，建立了TCP/IP网络的动态模型，为网络系统中动态性能的分析、拥塞控制策略的设计奠定了基础。实验结果表明，该数学模型与NS仿真实验的结果相一致。     

A study of multicast congestion control for UMTS

In this paper, we study the applicability of multicast congestion control over universal mobile telecommunications system (UMTS) networks. We analyze two well‐known multicast congestion control schemes for fixed networks, namely TCP‐friendly multicast congestion control and pragmatic general multicast congestion control. We investigate their behavior when they are employed in UMTS networks and we analyze the problems arose when these mechanisms are applied over the wireless links of the UMTS terrestrial radio‐access network. Additionally, we propose necessary improvements to these legacy schemes and explain the necessity of these modifications. The proposed schemes are implemented in the ns‐2 network simulator and are evaluated under various network conditions and topologies. Finally, we measure the performance of the proposed modified schemes and compare them with the corresponding legacy mechanisms. Copyright © 2009 John Wiley & Sons, Ltd.     

WiNoC中无线节点和无线链路级拥塞避免的高效路由器设计

无线片上网络中,无线网络拥塞可以分为无线节点级的拥塞和无线链路级的拥塞,这两种拥塞都会造成网络性能下降.针对无线节点和无线链路级拥塞,本文设计了一种拥塞避免的高效无线路由器,首先提出了节点级的拥塞避免机制,无线节点通过广播本地拥塞信息相互感知拥塞程度,避免向拥塞程度较高的无线节点发送数据包;其次提出了链路级拥塞避免机制,在无线接口中设计了并行FIFO,允许无线接口以流水的方式,在单个时钟周期内传输一个拥塞信息数据包和三个数据微片,数学建模证明使用并行FIFO至少降低50%无线信道竞争频率,从而避免了无线链路级拥塞,提高了无线资源利用率.实验表明本文方案相较普通无线路由器增加了少量的面积,但是在网络整体性能、无线路由器性能以及功耗方面都取得了不错的优势.