Wireless Power and Energy Harvesting Control in IoD by Deep Reinforcement Learning

Abstract

Internet of Drones (IoD), which deploys several drones in the air to collect ground information and send them to the IoD gateway for further processing, can be applied in traffic surveillance and disaster rescue. The performance of IoD is greatly affected by drones' battery capacities. We hence utilize the energy harvesting technology to charge the batteries and the wireless power control to adjust the drone wireless transmission power in order to address this challenge. In our work, we investigate the joint optimization of power control and energy harvesting control to determine each drone's transmission power and the transmitted energy from the charging station in time-varying IoD networks. Our objective is to minimize the long-term average system energy cost constrained by the drones' battery capacities and quality of service (QoS) requirements. A Markov Decision Process (MDP) is formulated to characterize the power and energy harvesting control process in time-varying IoD networks. A modified actor-critic reinforcement learning algorithm is then proposed to tackle our problem and its performance is demonstrated via extensive simulations.