Research on Mobile Edge Computing Task Offloading Strategy with Dual-Layer UAV Assistance

Aiming at the natural disaster scenarios where the base station is destroyed and the problem of insufficient computing power during UAV information collection, a double-layer UAV MEC system task offloading scheme is proposed. First, the B-UAV resource scheduling, offloading strategy and T-UAV mobility are jointly optimized to minimize the total system cost; second, the TD3-OPS algorithm is proposed by combining the TD3 algorithm, the state normalization process, the use of OU noise with simulated annealing idea, and the improvement of the preferred empirical replay mechanism; lastly, the simulation results show that the proposed algorithm converges faster compared to the baseline algorithm and can significantly reduce the total system cost.