Joint Energy Efficiency and Throughput Optimization for UAV-WPT Integrated Ground Network Using DDPG
Mohamed Amine Ouamri, Yasmina Machter, Daljeet Singh, Dina Alkama, Xingwang Li
Abstract
Unmanned aerial vehicles (UAV) have been applied in many civilian and commercial applications, including agriculture mapping, military surveillance, reconnaissance activities, and wireless communication. Due to the exponential increase in traffic demand and coverage hole problem, UAVs can be immediately deployed in the network to provide maximum wireless coverage and improve the quality of service (QoS) for users. However, to maintain communication while moving, the UAVs harvest energy from the RF signal of base stations in the ground. In this context, we propose a directional wireless power transfer (WPT) for charging UAVs by applying multi-beam energy in this letter. Two sub-problems are considered in our optimization problem which are energy efficiency (EE) and throughput maximization while taking into account interference from adjacent UAVs. Thus, to solve the formulated problem a deep deterministic policy gradient (DDPG) algorithm is implemented and compared to other deep reinforcement learning (DRL) methods.