Throughput for WPT-UAV Assisted Network Exploring TD3PG Algorithm

The unmanned aerial vehicles (UAV) acts as an airborne mobile base station to provide reliable and low-cost communication services to ground users in a fast and timely manner. It is a challenge to optimize UAVs resource allocation and coordinates to maximize throughput when wireless power transfer (WPT) technology is utilized to power UAVs. In this article, a multi-UAV assisted downlink network is investigated. To keep the UAVs running to guarantee the quality of service (QoS), a renewable energy powered wireless charging station is proposed to charge the UAVs with WPT. To improve the total throughput performance, the joint optimization of the UAVs position coordinates and the power control under the dynamic energy flow is research target. First, dynamic energy flow model from the ground to the air is mathematically constructed. Next, twin delayed deep deterministic policy gradient (TD3PG) algorithm is designed to jointly optimize the power control and position coordinates of the UAVs considering future channel gain and energy harvesting. Simulation results demonstrate that the proposed algorithm can improve the system throughput under dynamic energy flow compared to traditional optimization algorithms.