Optimizing CMT performance by joint predictions of bandwidth and RTT

Abstract

CMT uses the stream control transmission protocol's (SCTPs) multihoming feature to distribute data across multiple end-to-end paths in a multihomed SCTP association. As the disparity of multipaths, it is facing a great challenge to solve the disorder of the received data packets. To lighten the reordering degree and then to improve the throughput performance, we need to estimate the real-time paths' bandwidth and round trip time (RTT) as exactly as possible. In this paper, we use the extended vector (ext-vec) Kalman filter (KF) to predict the available bandwidth and RTT of each path simultaneously. Based on this, we propose a predictive path selection algorithm for CMT in SCTP. To simulate and compare the algorithms' performance, two kinds of scenarios, bandwidth sensitive scenario and time and bandwidth sensitive scenario, are built and NS-2 is used. The simulation results show that the path selection algorithm can lessen the data packets disordering by correctly predicting each path's bandwidth and RTT in real time. Comparing the existing algorithms, the algorithm can converge more quickly and can improve the system total throughput in a certain extent in bandwidth sensitive scenario. To time and bandwidth sensitive scenario, it can greatly improve the convergence speed and total throughput.