High-speed TCP Research Articles

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.

Performance evaluation of high speed TCP over optical burst switching networks

Study of TCP performance over OBS networks has been an important problem of research lately and it was found that due to the congestion control mechanism of TCP and the inherent bursty losses in the Optical Burst Switching (OBS) network, the throughput of TCP connections degrade. On the other hand, High Speed TCP (HSTCP) was proposed as an alternative to the use of TCP in high bandwidth-delay product networks. HSTCP aggressively increases the congestion window used in TCP, when the available bandwidth is high and decreases the window cautiously in response to a congestion event. In this work, we make a thorough simulation study of HSTCP over OBS networks. While the earlier works in the literature used a linear chain of nodes as the network topology for the simulation, we use the popular 14-node NSFNET topology that represents an arbitrary mesh network in our study. We also study the performance of HSTCP over OBS for different bandwidths of access networks. We use two different cases for simulations where in the first HSTCP connections are routed on disjoint paths while in the second they contend for resources in the network links. These cases of simulations along with the mesh topology help us clearly distinguish between the congestion and contention losses in the OBS network and their effect on HSTCP throughput. For completeness of study, we also simulate TCP traffic over OBS networks in all these cases and compare its throughput with that of HSTCP. We observe that irrespective of the access network bandwidth and the burst loss rate in the network, HSTCP outperforms TCP in terms of the throughput and robustness against multiple burst losses up to the expected theoretical burst loss probability of 10 −3.

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.

An algorithm for reducing loss rate of high-speed TCP

Some high-speed protocols such as HSTCP have been proposed to improve the ability of bandwidth utilization in high-speed networks. However, the increased scalability of high-speed TCP leads to many dropped packets in a single loss event in drop tail environment. In addition, there exists burstiness on short time scales that may cause lots of packets loss. In this paper, we analyze the problem of packet loss, and then propose ACWAP (Adaptive Congestion Window Adjustment plus Pacing) algorithm to reduce the loss rate of high-speed TCP. Along with pacing algorithm for avoiding burstiness on short time scales, ACWAP uses delay information to estimate the network state and adaptively changes the increase parameter to 1 before congestion to reduce the number of dropped packets. Many simulation results show our proposed algorithm can reduce the number of dropped packets in a single loss event, alleviate synchronized loss phenomena and improve the RTT unfairness while keeping the advantages of high-speed TCP.

Performance Evaluation and Comparison of Transport Protocols for Fast Long-Distance Networks

It is well known that TCP does not fully utilize the available bandwidth in fast long-distance networks. To solve this scalability problem, several high speed transport protocols have been proposed. They include Highspeed TCP (HS-TCP), Scalable TCP (S-TCP), Binary increase control TCP (BIC-TCP), and H-TCP. These protocols increase (decrease) their window size more aggressively (slowly) compared to standard TCP (STD-TCP). This paper aims at evaluating and comparing these high speed transport protocols through computer simulations. We select six metrics that are important for high speed protocols; scalability, buffer requirement, TCP friendliness, TCP compatibility, RTT fairness, and responsiveness. Simulation scenarios are carefully designed to investigate the performance of these protocols in terms of the metrics. Results clarify that each high speed protocol successfully solves the problem of STD-TCP. In terms of the buffer requirement, S-TCP and BIC-TCP have better performance. For TCP friendliness and compatibility, HS-TCP and H-TCP offer better performance. For RTT fairness, BIC-TCP and H-TCP are superior. For responsiveness, HS-TCP and H-TCP are preferred. However, H-TCP achieves a high degree of fairness at the expense of the link utilization. Thus, we understand that all the proposed high speed transport protocols have their own shortcomings. Thus, much more research is needed on high speed transport protocols.

Experimental Results of Implementing High-Speed and Parallel TCP Variants for Long Fat Networks

As computer hardware components are achieving greater speeds, network link bandwidths are becoming wider. A number of enhancements to TCP have been developed in order to fully exploit these improvements in network infrastructures, including TCP window scale option, SACK option, and Highspeed TCP (HSTCP) modifications. However, even with these enhancements, TCP cannot provide satisfactory performance in high-speed long-delay networks. As a means addressing this problem, gentle Highspeed TCP (gHSTCP) has been proposed in [1]. However, its effectiveness has only been demonstrated in simulation experiments. In the present paper, a refined gHSTCP algorithm is proposed for application to real networks. The performance of the refined gHSTCP algorithm is then assessed experimentally. The refined gHSTCP algorithm is based on the original algorithm, which uses two modes (Reno mode and HSTCP mode) in the congestion avoidance phase and switches modes based on RTT increasing trends. The refined gHSTCP algorithm compares two RTT thresholds and judges which mode will be used. The performance of gHSTCP is compared with TCP Reno/HSTCP and parallel TCP mechanisms. The experimental results demonstrate that gHSTCP can provide a better tradeoff in terms of utilization and fairness against co-existing traditional TCP Reno connections, whereas HSTCP and parallel TCP suffer from the trade-off problem.

Generalized Modeling and Stability Analysis of HighSpeed TCP and Scalable TCP

In this letter we examine two transport protocols, High-Speed TCP [1] and Scalable TCP [2] which are both sender-side varieties of TCP. Based on the fluid flow theory, we develop a general nonlinear model and use gain margin and phase margin to evaluate the stability of a closed-loop system which is composed of a transport protocol and an active queue management scheme. Our results indicate that HSTCP and STCP are stabler than standard TCP when link bandwidth, flow number and round-trip time vary.

A Simulation Study of Scalable TCP and HighSpeed TCP in Geostationary Satellite Networks

This paper investigates the performance of two TCP enhancements (i.e., Scalable TCP and HighSpeed TCP), recently proposed for high-speed backbone networks with a very large bandwidth-delay product, in a geostationary satellite environment. Both persistent and elastic traffic patterns are considered, performance being evaluated in terms of TCP throughput and mean session delay, respectively. The impact of channel characteristics (packet error rate, correlation between successive losses) is widely discussed. Fairness issues are also accounted for, together with the impact of some system parameters, such as the satellite link bandwidth. Extensive comparisons are carried out among Scalable TCP, HighSpeed TCP and other congestion control schemes. The obtained results show the soundness for the use of such protocols in geostationary satellite networks. Indeed, both protocols permit to improve the performance of TCP connections in a wide range of channel conditions, showing (especially Scalable TCP) to be able to cope well with rainy conditions and to exploit a future increase in the satellite link capacity.

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.

Comparative Study of Different Adaptive Window Protocols

We study an Adaptive Window Protocol (AWP) with general increase and decrease profiles in the presence of window dependent random losses. We derive a steady-state Kolmogorov equation, and then obtain its solution in analytic form for particular TCP versions proposed for high speed networks, such as Scalable TCP and HighSpeed TCP. We also relate window evolution under an AWP to workload process in queueing systems; this observation gives us a way to compare various AWP protocols.

Exponential-RED: a stabilizing AQM scheme for low- and high-speed TCP protocols

This paper introduces and analyzes a decentralized network congestion control algorithm which has dynamic adaptations at both user ends and link ends, a so-called general primal-dual algorithm. We obtain sufficient conditions for local stability of this algorithm in a general topology network with heterogeneous round-trip delays. Then, as an implementation of this algorithm in the Internet, we introduce an AQM (Active Queue Management) scheme called Exponential-RED (E-RED), which outperforms RED and is inherently stable when combined with TCP-Reno or its variants for high-speed networks.

Performance Analysis and Improvement of HighSpeed TCP with TailDrop/RED Routers

Continuous and explosive growth of the Internet has shown that current TCP mechanisms can obstruct efficient use of high-speed, long-delay networks. To address this problem we propose an enhanced transport-layer protocol called gHSTCP, based on Highspeed TCP proposed by Sally Floyd. It uses two modes in the congestion avoidance phase based on the changing trend of RTT. Simulation results show gHSTCP can significantly improve performance in mixed environments, in terms of throughput and fairness against the traditional TCP Reno flows. However, the performance improvement is limited due to the nature of TailDrop router, and the RED/ARED routers can not alleviate the problem completely. Therefore, we present a modified version of Adaptive RED, called gARED, directed at the problem of simultaneous packet drops by multiple flows in high speed networks. gARED can eliminate weaknesses found in Adaptive RED by monitoring the trend in variation of the average queue length of the router buffer. Our approach, combining gARED and gHSTCP, is quite effective and fair to competing traffic than Adaptive RED with Highspeed TCP.

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.

Throughput of high-speed TCP in optical burst switching networks

High-speed TCP (HSTCP) has been proposed to achieve high throughput in the high bandwidth and long-delay environment. The throughput of HSTCP is studied when the backbone network adopts the optical burst switching (OBS) technology. The study shows that small burst assembly time and a large burst loss ratio in OSB can reduce the throughput of HSTCP significantly, but HSTCP still performs much better than TCP.

Microscopic examination of TCP flows over transatlantic links

Much of the recent research and development in the area of high-speed TCP is focused on the steady state behavior of TCP flows. However, our experience with the first research only transatlantic 2.5 Gbps Lambda link clearly demonstrates the need to focus on the initial stages of TCP. The work we present here examines the behavior of TCP flows at microscopic level over high-bandwidth long delay networks. This examination has led us to study the influence of the minute properties of the underlying network on bursty protocols such as TCP at these very high speeds combined with high latency. In this paper we briefly describe the requirements for such an extreme network environment to support high-speed TCP flows. We also present results collected using transatlantic links at iGrid2002 where we tuned various host parameters and used modified TCP stacks.

End system optimizations for high-speed TCP

The delivered TCP performance on high-speed networks is often limited by the sending and receiving hosts, rather than by the network hardware or the TCP protocol implementation itself. In this case, systems can achieve higher bandwidth by reducing host overheads through a variety of optimizations above and below the TCP protocol stack, given support from the network interface. This article surveys the most important of these optimizations and illustrates their effects quantitatively with empirical results from an experimental network delivering up to 2 Gb/s of end-to-end TCP bandwidth.

The incremental deployability of RTT-based congestion avoidance for high speed TCP Internet connections

Our research focuses on end-to-end congestion avoidance algorithms that use round trip time (RTT) fluctuations as an indicator of the level of network congestion. The algorithms are referred to as delay-based congestion avoidance or DCA. Due to the economics associated with deploying change within an existing network, we are interested in an incrementally deployable enhancement to the TCP/Reno protocol. For instance, TCP/Vegas, a DCA algorithm, has been proposed as an incremental enhancement. Requiring relatively minor modifications to a TCP sender, TCP/Vegas has been shown to increase end-to-end TCP throughput primarily by avoiding packet loss. We study DCA in today's best effort Internet where IP switches are subject to thousands of TCP flows resulting in congestion with time scales that span orders of magnitude. Our results suggest that RTT-based congestion avoidance may not be reliably incrementally deployed in this environment. Through extensive measurement and simulation, we find that when TCP/DCA (i.e., a TCP/Reno sender that is extended with DCA) is deployed over a high speed Internet path, the flow generally experiences degraded throughput compared to an unmodified TCP/Reno flow. We show (1) that the congestion information contained in RTT samples is not sufficient to predict packet loss reliably and (2) that the congestion avoidance in response to delay increase has minimal impact on the congestion level over the path when the total DCA traffic at the bottleneck consumes less than 10% of the bottleneck bandwidth.