Multi-agent Congestion Control for High-Speed Networks Using Reinforcement Co-learning

Abstract

This paper proposes an adaptive reinforcement co-learning method for solving congestion control problems on high-speed networks. Conventional congestion control scheme regulates source rate by monitoring queue length restricted to a predefined threshold. However, the difficulty of obtaining complete statistics on input traffic to a network. As a result, it is not easy to accurately determine the effective thresholds for high-speed networks. We proposed a simple and robust Co-learning Multi-agent Congestion Controller (CMCC), which consists of two subsystems: a long-term policy evaluator and a short-term rate selector incorporated with a co-learning reinforcement signal to solve the problem. The well-trained controllers can adaptively take correct actions to regulate source flow under time-varying environments. Simulation results showed the proposed approach can promote the system utilization and decrease packet losses simultaneously.