Intelligent Reflecting Surface Aided Mobile Edge Computing with Rate-Splitting Multiple Access

Recently, intelligent reflecting surface (IRS) has emerged as a promising technology, which can be applied in mobile edge computing (MEC) systems to achieve higher data transmission efficiency and reliability, by providing a reflective channel. Concurrently, rate-splitting multiple access (RSMA), as an innovative technology, is increasingly utilized in MEC systems to enhance data offloading efficiency and facilitate a better integration of computation and communication. In this paper, an IRS enabled MEC system with RSMA under user mobility is considered. Based on this system model, we propose an optimization problem that is aimed at maximizing the system's data transmission rate by jointly optimizing the RSMA power allocation and the IRS phase shift parameters. Although traditional optimization methods can be utilized to solve the considered problem, it is quite time consuming since the optimization methods are often iterative algorithms. To design low complexity algorithm, we propose a deep reinforcement learning (DRL) approach that can efficiently make good decisions quickly after training. Numerical results indicate that, compared to the baseline algorithms, the proposed DRL-based IRS-aided offloading algorithm under RSMA protocol achieves superior system performance.