Computation offloading optimization for UAV-assisted power industrial internet of things mobile edge computing system

With the advancement of the power industrial internet of things (PIIoT), the volume of data generated by intelligent power devices in smart power plants is rapidly increasing. Large-scale real-time data processing necessitates the utilization of edge servers’ computational capabilities to reduce delay and energy consumption. Meanwhile, unmanned aerial vehicles (UAVs), with their flexible deployment and wide coverage, play a significant role in enhancing communication quality within mobile edge computing (MEC) systems. To address the computational demands in PIIoT scenarios, this paper introduces a UAV-assisted PIIoT MEC system, where UAVs provide processing support to nearby PDGs by accepting offloaded tasks. The remaining workloads are computed locally by the PDGs. Facing the challenges posed by discrete control variables and energy constraints, we perform joint optimization of scheduling, offloading decisions, and UAV mobility parameters to reduce the overall delay-energy trade-off. To effectively solve this complex, non-convex problem characterized by a large state–action space, this paper propose a deep deterministic policy gradient-based computation offloading optimization (DDPG-COO) algorithm. Simulation results confirm the fast convergence behavior of the proposed DDPG-COO scheme. Compared to existing baselines, notable enhancements are observed in delay reduction and energy saving performance.