Meta Reinforcement Learning-Based Computation Offloading in RIS-Aided MEC-Enabled Cell-Free RAN

Yi Lu, Yanxiang Jiang, Lingling Zhang, Mehdi Bennis, Dusit Niyato, Xiaohu You

Abstract: In this paper, the computation offloading problem in reconfigurable intelligent surface (RIS)-aided mobile edge computing (MEC)-enabled cell-free radio access network (CF-RAN) is investigated. To minimize the average task execution delay, we propose to formulate a joint optimization problem of computation offloading and RIS phase shifts. Considering the non-deterministic polynomial hard (NP-hard) property of this problem and time-varying network environment, we further propose a meta reinforcement learning (meta-RL)-based computation offloading policy, which can adapt to new environment quickly with only a few gradient updates. By aggregating powerful decision-making ability of conventional RL and rapid environment learning ability of meta-learning, our proposed policy can find the optimal strategy in very fast speed. Simulation results show that our proposed meta-RL-based computation offloading policy reduces the average task execution delay by 25% compared to the considered two state-of-the-art benchmark policies.