Joint User Scheduling and Beam Selection in mmWave Networks Based on Multi-Agent Reinforcement Learning

Abstract

In this paper, we consider a multi-cell downlink mmWave communication network and investigate an efficient transmission scheme for all base stations. Since the beams are highly directed with respected to the user equipments, user scheduling and beam selection strategy should be jointly considered. The objective is to develop the joint user scheduling and beam selection strategy that minimizes the long-term average delay cost while satisfying the instantaneous quality of service constraint of each user. To achieve the long-term performance, a distributed algorithm is proposed to develop the joint strategy based on multi-agent reinforcement learning. Simulation results validate the effectiveness of the proposed intelligent distributed method.