Hierarchical Learning for IRS-Assisted MEC Systems with Rate-Splitting Multiple Access

TL;DR

The paper tackles latency minimization in IRS-assisted MEC systems employing RSMA by jointly optimizing passive/active beamforming, offloading, power, RSMA splits, and decoding order. It introduces a hierarchical DRL framework (CDEH) that combines TD3 for continuous decisions and DQN for discrete decoding-order decisions, aided by a CNN-DenseNet network to extract rich channel features from CSI matrices. The method demonstrates strong convergence and outperforms benchmarks, particularly by leveraging a novel uplink RSMA interference management strategy and effective IRS/beamforming optimization. The results indicate meaningful performance gains in terms of lower average delay and robustness across varying IRS elements, power levels, and user counts, highlighting the approach’s practical potential for dense B5G/6G MEC networks.

Abstract

Intelligent reflecting surface (IRS)-assisted mobile edge computing (MEC) systems have shown notable improvements in efficiency, such as reduced latency, higher data rates, and better energy efficiency. However, the resource competition among users will lead to uneven allocation, increased latency, and lower throughput. Fortunately, the rate-splitting multiple access (RSMA) technique has emerged as a promising solution for managing interference and optimizing resource allocation in MEC systems. This paper studies an IRS-assisted MEC system with RSMA, aiming to jointly optimize the passive beamforming of the IRS, the active beamforming of the base station, the task offloading allocation, the transmit power of users, the ratios of public and private information allocation, and the decoding order of the RSMA to minimize the average delay from a novel uplink transmission perspective. Since the formulated problem is non-convex and the optimization variables are highly coupled, we propose a hierarchical deep reinforcement learning-based algorithm to optimize both continuous and discrete variables of the problem. Additionally, to better extract channel features, we design a novel network architecture within the policy and evaluation networks of the proposed algorithm, combining convolutional neural networks and densely connected convolutional network for feature extraction. Simulation results indicate that the proposed algorithm not only exhibits excellent convergence performance but also outperforms various benchmarks.

Figures (14)

• Figure 1: IRS-assisted MEC system.
• Figure 2: The complete structure of neural network.
• Figure 3: The workflow of proposed CDEH algorithm.
• Figure 4: Training rewards for different network structures.
• Figure 5: Training rewards for different algorithms.