Abstract
Edge computing-assisted unmanned aerial vehicle (UAV) networks are emerging as a prospective low-altitude economy (LAE) framework to provide extensive computing and communication services for Internet of Things (IoT) terminals. Considering that wireless signals may be easily blocked by obstacles, this paper leverages reconfigurable intelligent surface (RIS) to improve the propagation environment for low-altitude wireless networks (LAWNs). We aim to reduce the total system energy consumption of LAWNs, by jointly optimizing the RIS phase shift, power allocation, computation offloading and resource allocation. To address this non-convex problem, we decompose the original problem into two tractable subproblems, which are solved respectively using local search method, and a deep reinforcement learning (DRL)-based proximal policy optimization (PPO) algorithm. Finally, simulation results show that the proposed algorithm achieves better convergence and effectively reduces the energy consumption compared with other benchmark schemes.