UAV-Assisted 5G/6G Networks: Joint Scheduling and Resource Allocation Based on Asynchronous Reinforcement Learning

Unmanned aerial vehicles (UAVs) can be used as flying base stations (BSs) for providing wireless communications and coverage enhancement in fifth/sixth-generation (5G/6G) wireless networks. Operating multiple UAV-BSs to guarantee reliable device connectivity, intelligent control of UAV movements, and resource allocation plays an important role in dynamic UAV-assisted wireless networks. In this paper, an asynchronous advantage actor-critic (A3C) based UAVs placement and resource allocation approach is proposed to maximize the network capacity while guaranteeing the wireless service requirements of ground devices. The approach enables UAVs to intelligently update their locations and resource allocation strategy according to devices' locations, to support the favourable channel gain between UAVs and devices, and maximize network benefit. Simulations show that our presented approach achieves higher learning efficiency, network capacity and QoS satisfaction level compared to popular approaches.