IRS-Aided Mobile Edge Computing for Mine IoT Networks using Deep Reinforcement Learning

Recent years have witnessed a growing interest in implementing mobile edge computing (MEC) into mine Internet of Things (IoT) networks to enable real-time monitoring and safety management. However, the spatial blockage and limited transmitting power pose challenges to signal coverage and efficient computation offloading. To address these issues, we propose incorporating intelligent reflecting surfaces (IRSs) in the MEC system for underground mines (MMEC) to resolve wireless coverage problems in mine communication scenarios and enhance the channel gains of offloading links. Given the time-varying and complex channel conditions in mines and the multiple coupled variables involved in IRSs’ reflecting coefficient matrix, we utilize Deep Reinforcement Learning (DRL) to acquire the optimal IRS-assisted computation offloading strategy in dynamic mine environments. Specifically, we propose a Deep Deterministic Policy Gradient (DDPG)-based IRS-aided computation offloading scheme to jointly optimize the IRS elements’ reflection coefficients and the computation offloading rate. Simulation results demonstrate that introducing an IRS into the MMEC system yields outstanding benefits and significantly exceeds benchmarks in enhancing energy efficiency and decreasing computational latency.