Privacy-Preserving Computation Offloading and 3-D Trajectory Optimization in Multi-UAV-Assisted MEC System

Due to the flexibility in the deployment of unmanned aerial vehicles (UAVs), UAV-assisted mobile edge computing (MEC) systems have garnered significant attention in recent years. Users can offload computational tasks to MEC servers to meet low-latency demands. However, this offloading approach may expose users’ location privacy and usage pattern privacy. Therefore, we investigate a privacy-preserving task offloading scheme in a multi-UAV-assisted MEC system. The objective is to minimize latency while achieving high fairness among UAVs, by jointly optimizing the offloading strategy, user selection policy, and 3D trajectories of UAVs under the constraints of privacy preservation and load fairness. To solve this complex problem, we propose a Twin Delayed Deep Deterministic (TD3) - Fairness-Aware Privacy Preservation and Trajectory Optimization algorithm (TD3-FAPPTO). Specifically, we first derive the optimal user selection policy through theoretical analysis, and then the differential privacy technique is applied to perturb the original offloading ratio. Finally, we employ the TD3 algorithm to optimize offloading strategy and multi-UAV flight trajectories. The simulation results demonstrate that the proposed algorithm achieves superior performance in maintaining lower system costs while satisfying the strict and time-varying privacy-preserving requirements of each user.