Fast fairness convergence through fair rate estimation in Variable-structure congestion Control Protocol

Abstract

Traditional Transmission Control Protocol (TCP) faces significant limitations such as unclear congestion implication, low utilization in high-speed networks, unstable throughput and limited fairness. In order to overcome such limitations, numerous research works have been done in effective congestion control algorithms. Among these, Variable-structure congestion Control Protocol (VCP) leverages only the existing two explicit congestion notification bits for network congestion feedback, yet achieves high utilization, low persistent queue length, negligible packet loss rate and reasonable fairness. However, VCP converges to fairness relatively slowly due to its large multiplicative decrease parameter. To address this problem, we propose an end-host based method for fast fairness convergence, namely VCP-FFC (VCP with fast fairness convergence). In each Additive Increase and Multiplicative Decrease (AIMD) epoch, VCP-FFC estimates a fair rate in end-hosts, and adjusts the congestion window according to the fair rate to achieve fast fairness convergence. We evaluate the performance of VCP-FFC over a wide range of network scenarios using NS2. Simulation Results show that VCP-FFC not only maintains the good properties of VCP, but also significantly accelerates fairness convergence. Dynamic analysis shows that VCP-FFC is asymptotically stable and converges to a unique stationary point, i.e. the fair rate share.