High-speed TCP Protocols Research Articles

Analysis of multiple flows using different high speed TCP protocols on a general network

We develop analytical tools for performance analysis of multiple TCP flows (which could be using TCP CUBIC, TCP Compound, TCP New Reno) passing through a multi-hop network. We first compute average window size for a single TCP connection (using CUBIC or Compound TCP) under random losses. We then consider two techniques to compute steady state throughput for different TCP flows in a multi-hop network. In the first technique, we approximate the queues as M/G/1 queues. In the second technique, we use an optimization program whose solution approximates the steady state throughput of the different flows. Our results match well with ns2 simulations.

Fairness of High-Speed TCP Protocols with Different Flow Capacities

Nowadays, the performance evaluation of high-speed TCP protocols is the subject of intensive research. The main criteria used to evaluate the performance are: Fairness, Backward compatibility, Efficiency, Responsiveness, Scalability, TCP friendliness, and convergence. Most of researches were conducted to evaluate fairness. The majority of these researches used only two flows in a Dumbbell topology. Only few papers used several flows. In all cases, to the best of our knowledge, all flows have the same capacity which may not give an accurate idea about Fairness of different protocols and impact performance results. We propose an evaluation method of Fairness for different high-speed protocols: HTCP, HS-TCP, Scalable TCP, BIC-TCP and CUBIC protocols using multiple flows with the same flow capacity, and with different flow capacities.

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.