This paper introduces an innovative closed-loop traffic controller to efficiently and fairly share a single common resource, e.g., the available bit rate in a wireless link, among a set of traffic flows characterized by different Quality of Service (QoS) requirements. The proposed traffic controller relies on a control-based approach that exploits a closed-loop feedback architecture including Proportional-Integral-Derivative (PID) controllers that are dynamically tuned using fuzzy logic. The traffic controller is able to react to different scenarios and traffic load conditions, while targeting the twofold objective of maximizing the resource utilization and respecting the flow QoS requirements. Simulation results demonstrate that the proposed closed-loop traffic controller outperforms a well-known open-loop traffic controller (based on Dual Leaky Buckets (DLBs) and Earliest Deadline First (EDF) scheduling algorithm.
/lp/association-for-computing-machinery/a-closed-loop-fuzzy-traffic-controller-for-fair-bandwidth-sharing-iju4rl5MdP