Improving Fairness and Convergence Efficiency of TCP Traffic in Multi-hop Wireless Networks

Last-mile telecommunication networks witnessed phenomenal growth in using multi-hop wireless technologies to improve capacity and radio coverage for a longer extent. The penetration of wireless internet in last-mile multi-hop networks has significantly altered our routine lifestyle. Most internet applications heavily rely on transmission control protocol (TCP) to reliably deliver data packets between the sender-receiver processes. However, the fairness and steady-state convergence performance of TCP data traffic in the multi-hop radio networks (MRN) remain plagued by spurious rate reduction, flat rate cut, and low convergence limitations. The feedback-assisted improved recovery (FAIR) algorithm proposed in this article adopts three strategies to strengthen TCP's performance in the MRN. Initiate the congestion avoidance based on intermediate node queue accumulation, TCP's growth-based proportionate rate reduction method, and a rapid recovery mechanism. The MRN simulation experiments decisively demonstrate the substantial improvement in steady-state convergence time, flow fairness, throughput, and packet latency performances of the FAIR algorithm against RFC 6582, NRT, and OQS approaches.