부산대학교 도서관

Optimizing the trajectory of Unmanned Aerial Vehicle (UAV) Base Station (BS) is an important operational task to improve the Quality of Service (QoS) for remote areas. However, existing works mainly neglect the fair coverage and dynamic Ground Users (GUs). In this paper, we propose a novel coverage fairness index (CFI) to measure whether dynamic GUs are served as fairly as possible. Then, we formulate the problem as a constrained problem with the objective of maximizing fair coverage and minimizing energy consumption while satisfying the bound constraints. An accurate and efficient Soft-Actor-Critic (SAC)-based UAV trajectory optimization algorithm is proposed to solve the complex constrained problem based on deep reinforcement learning. Experiments are executed to prove the feasibility and efficiency of the proposed algorithm. The results manifest that the performance of the proposed algorithm is better than that of the two existing baseline methods.