Partial Task Offloading and UAV Trajectory Design in Air-Ground Integrated Mobile Edge Computing Network

The integration of mobile edge computing (MEC) with the air-ground integrated network is viewed as a crucial technology for Internet of remote things (IoRT) devices, where the tasks of IoRT devices can be executed by the unmanned aerial vehicle (UAV) and the high altitude platform. In this paper, we study a partial task offloading and UAV trajectory design problem to minimize the total task offloading delay in the air-ground integrated MEC network. Since the problem is non-convex, we transform it into a Markov decision process (MDP). Considering the complexity of the MDP increases with the number of the IoRT devices and the UAVs, we divide the problem into two subproblems: the UAV trajectory design subproblem, and the partial task offloading and resource allocation subproblem. For these two subproblems, we utilize deep deterministic policy gradient and proximal policy optimization to solve them, respectively. Based on the two methods, a partial task offloading and UAV trajectory design (PTOUTD) algorithm is proposed. Simulation results show the proposed PTOUTD algorithm can achieve a reduction in total offloading delay.