A Dual-Agent Approach for Coordinated Task Offloading and Resource Allocation in MEC

Multiaccess edge computing (MEC) is a novel distributed computing paradigm. In this paper, we investigate the challenges of task offloading scheduling, communication bandwidth, and edge server computing resource allocation for multiple user equipments (UEs) in MEC. Our primary objective is to minimize system latency and local energy consumption. We explore the binary offloading and partial offloading methods and introduce the dual agent-TD3 (DA-TD3) algorithm based on the deep reinforcement learning (DRL) TD3 algorithm. The proposed algorithm coordinates task offloading scheduling and resource allocation for two intelligent agents. Specifically, agent 1 overcomes the action space explosion problem caused by the increasing number of UEs, by utilizing both binary and partial offloading. Agent 2 dynamically allocates communication bandwidth and computing resources to adapt to different task scenarios and network environments. Our simulation experiments demonstrate that the binary and partial offloading schemes of the DA-TD3 algorithm significantly reduce system latency and local energy consumption compared with deep deterministic policy gradient (DDPG) and other offloading schemes. Furthermore, the partial offloading optimization scheme performs the best.