Joint Energy and AoI Optimization in UAV-assisted MEC-WET Systems

In this paper, we propose an unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) and wireless energy transfer (WET) network in disaster scenarios, where both the data-processing UAVs (DP-UAVs) and the energy-transferring UAVs (ET-UAVs) are deployed. To ensure the freshness of data, the age of information (AoI) is utilized on both user equipment (UE) and the data center (DC). An optimization problem is formulated to minimize the AoI and the energy consumption of the UAVs by jointly optimizing the UAVs’ trajectories and offloading strategies. To find the optimal solution, the problem is decomposed into two optimization subproblems: the trajectory planning and offloading policy design. Then, the modified multi-agent deep deterministic policy gradient (M2DDPG) algorithm and the traversal-based greedy (TG) algorithm are proposed to solve the two subproblems respectively, where the cooperation of the UAVs and the greedy-choice property of the problem are fully utilized. Simulation results validate the effectiveness of the proposed M2DDPG-TG algorithm and demonstrate that it performs better than the baseline algorithms and the traditional MADDPG algorithm. The scalability of the proposed algorithms is also verified by extensive simulations.