Joint Optimization of Task Offloading, Resource Allocation, and Trajectory Design in Cooperative Multi-UAV MEC Networks

Uncrewed Aerial Vehicle (UAV)-assisted Mobile Edge Computing (MEC) systems provide flexible and resilient computing capabilities for mobile users by leveraging UAVs as edge servers (ESs). However, in practical deployments, user devices typically exhibit spatially non-uniform distributions, which impose significant challenges for achieving optimal UAV placement. Conventional fixed or pre-determined deployment strategies cannot dynamically adapt to heterogeneous user distributions. To overcome these challenges, this article investigates an air–ground cooperative MEC architecture comprising multiple UAVs and terrestrial ESs. A multi-objective optimization problem incorporating UAV trajectory optimization is formulated to jointly minimize task offloading latency and total system energy consumption. As the problem is an NP-hard mixed-integer nonlinear programming model, a Joint Alternating Optimization framework for Task Offloading, Resource Allocation, and UAV Trajectory control (JAOTRU) is proposed. The JAOTRU framework adopts an iterative block coordinate descent structure to decouple the highly coupled optimization variables into two subproblems, which are efficiently solved via a differential evolution algorithm and a successive convex approximation technique, respectively. The simulation results show that the proposed JAOTRU method substantially surpasses several benchmark methods regarding total offloading latency and system energy efficiency, validating its effectiveness and robustness for MEC systems assisted by UAVs.