Secrecy Energy Efficiency Maximization in IRS-Assisted VLC MISO Networks with RSMA: A DS-PPO approach

TL;DR

This paper proposes a deep reinforcement learning method to optimize secrecy energy efficiency in IRS-assisted VLC MISO networks using RSMA, achieving significant performance improvements over traditional schemes.

Contribution

It introduces a novel DS-PPO approach for joint optimization in IRS-assisted VLC networks with RSMA, addressing non-convexity and NP-hardness.

Findings

DS-PPO outperforms traditional baselines in SEE.

Achieves approximately 19.67% improvement over traditional schemes.

Achieves approximately 25.74% improvement with IRS deployment.

Abstract

This paper investigates intelligent reflecting surface (IRS)-assisted multiple-input single-output (MISO) visible light communication (VLC) networks utilizing the rate-splitting multiple access (RSMA) scheme. {In these networks,} an eavesdropper (Eve) attempts to eavesdrop on communications intended for legitimate users (LUs). To enhance information security and energy efficiency simultaneously, we formulate a secrecy energy efficiency (SEE) maximization problem. In the formulated problem, beamforming vectors, RSMA common rates, direct current (DC) bias, and IRS alignment matrices are jointly optimized subject to constraints on total power budget, quality of service (QoS) requirements, linear operating region of light emitting diodes (LEDs), and common information rate allocation. Due to the non-convex and NP-hard nature of the formulated problem, we propose a deep reinforcement learning (DRL)-based dual-sampling proximal policy optimization (DS-PPO) approach. {The approach leverages} dual sample strategies and generalized advantage estimation (GAE). In addition, to further simplify the design, we adopt the maximum ratio transmission (MRT) and zero-forcing (ZF) as beamforming vectors in the action space. Simulation results show that the proposed DS-PPO approach outperforms traditional baseline approaches in terms of achievable SEE and significantly improves convergence speed compared to the original PPO approach. Moreover, implementing the RSMA scheme and IRS contributes to overall system performance, {achieving approximately $19.67\%$ improvement over traditional multiple access schemes and $25.74\%$ improvement over networks without IRS deployment.