Dynamic Task Offloading and Resource Allocation for Air-Ground Integrated Networks Based on MADDPG

Abstract

With the rapid growth of connected devices, traditional edge-cloud systems are under overload pressure. Using mobile edge computing (MEC) to assist unmanned aerial vehicles (UAVs) as low altitude platform stations (LAPS) for communication and computation to build air-ground integrated networks (AGINs) offers a promising solution for seamless network coverage of remote internet of things (IoT) devices in the future. To address the performance demands of future mobile devices (MDs), we proposed an MEC-assisted AGIN system. The goal is to minimize the long-term computational overhead of MDs by jointly optimizing transmission power, flight trajectories, resource allocation, and offloading ratios, while utilizing non-orthogonal multiple access (NOMA) to improve device connectivity of large-scale MDs and spectral efficiency. We first designed an adaptive clustering scheme based on K-Means to cluster MDs and established communication links, improving efficiency and load balancing. Then, considering system dynamics, we introduced a partial computation offloading algorithm based on multi-agent deep deterministic policy gradient (MADDPG), modeling the multi-UAV computation offloading problem as a Markov decision process (MDP). This algorithm optimizes resource allocation through centralized training and distributed execution, reducing computational overhead. Simulation results show that the proposed algorithm not only converges stably but also outperforms other benchmark algorithms in handling complex scenarios with multiple devices.

Keywords

air-ground integrated network (AGIN) / resource allocation / dynamic task offloading / multi-agent deep deterministic policy gradient (MADDPG) / non-orthogonal multiple access (NOMA)