Energy-Efficient Multi-Agent Deep Reinforcement Learning Task Offloading and Resource Allocation for UAV Edge Computing

Abstract

The integration of Unmanned Aerial Vehicles (UAVs) into Mobile Edge Computing (MEC) systems has emerged as a transformative solution for latency-sensitive applications, leveraging UAVs’ unique advantages in mobility, flexible deployment, and on-demand service provisioning. This paper proposes a novel multi-agent reinforcement learning framework, termed Multi-Agent Twin Delayed Deep Deterministic Policy Gradient for Task Offloading and Resource Allocation (MATD3-TORA), to optimize task offloading and resource allocation in UAV-assisted MEC networks. The framework enables collaborative decision making among multiple UAVs to efficiently serve sparsely distributed ground mobile devices (MDs) and establish an integrated mobility, communication, and computational offloading model, which formulates a joint optimization problem aimed at minimizing the weighted sum of task processing latency and UAV energy consumption. Extensive experiments demonstrate that the algorithm achieves improvements in system latency and energy efficiency compared to conventional approaches. The results highlight MATD3-TORA’s effectiveness in addressing UAV-MEC challenges, including mobility–energy tradeoffs, distributed decision making, and real-time resource allocation.