On Minimizing TCP Traffic Congestion in Vehicular Internet of Things (VIoT)

Abstract

The performance of end-to-end wireless link congestion control algorithm in the vehicular internet of things network is plagued by the inherent limitations of spurious rate control initiation, slow convergence time, and fairness disparity. In this article, the delay assisted rate tuning (DART) approach is proposed for the vehicular network that implements two algorithms, utilization assisted reduction (UAR) and super linear convergence (SLC), to overcome the transmission control protocol (TCP) limitations. The UAR algorithm is responsible for initiating the proportionate rate control process based on the bottleneck prediction parameter, thereby regulating the needless rate control during non-congested losses. In the congestion recovery mode, the SLC algorithm executes a dynamic rate update mechanism that enhances the flow rate and minimizes bandwidth sharing disparity among TCP flows. An analytical model was developed to study the DART convergence rate and fairness performance against the existing algorithm. The vehicular simulation outcome also confirms significant enhancement in average transmission rate, average message latency, and average bandwidth sharing performances of the DART algorithms against the RFC 6582, TCP-LoRaD, and CERL + congestion avoidance algorithms under varying traffic flows and node movement scenarios.