Robust Transmission Design for RIS-Aided Full-Duplex-RSMA V2X Communications via Multi-Agent DRL

The proliferation of mobile devices and acceleration of spectral efficiency have become a pivotal requirement for the unprecedented connectivity, and performance of vehicle-to-everything (V2X) networks. This paper investigates an unconventional framework of reconfigurable intelligent surface (RIS)-integrated full-duplex (FD) rate-splitting multiple access (RSMA) communication systems, which aims to maximize the spectral efficiency of the V2X network. In particular, a robust spectral-efficient design for the considered RIS-integrated FD-RSMA system via joint beamforming design, and power allocation under imperfect channel state information is investigated. To tackle the non-convexity of the original sum-rate maximization problem, we adopt a deep reinforcement learning (DRL)-based multi-agent (MA) proximal policy optimization (PPO) algorithm which leverages Markov decision process (MDP) formulation. Simulation results demonstrate the effectiveness of the integration of RIS, RSMA, and FD schemes for V2X networks over half-duplex (HD) and multi-user linear precoding schemes. Furthermore, the superiority of the proposed MA-PPO algorithm is validated over the counterpart PPO, and deep deterministic policy gradient algorithm (DDPG). Additionally, adopting RSMA yields a substantial 34.8$\%$ performance boost compared to SDMA at 50 m/s velocity, highlighting RSMA's adaptive robustness amidst dynamic CSI fluctuations in vehicular networks.

I. Introduction

The realm of vehicular communication is undergoing a rapid and transformative evolution, primarily catalyzed by the emergence of vehicle-to-everything (V2X) communication [1]. This revolutionary paradigm encompasses a spectrum of interactions between vehicles and their surrounding environment, encompassing not just vehicle-to-vehicle (V2V) connections but also extending to interactions with infrastructure (V2I), pedestrians (V2P), and various elements within the vehicular ecosystem. This shift signifies a fundamental departure from conventional vehicular interactions, introducing a new era of interconnected and intelligent transportation systems [2]. However, this profound advancement is accompanied by a set of formidable challenges. Foremost among these is the imperative to judiciously harness the finite and constrained resource of the radio frequency (RF) spectrum among multiple vehicles (or users). Moreover, the functionality of vehicular networks is heavily reliant on stable channel conditions, which is problematic due to the challenges posed by the high mobility of vehicles in wireless communications. Intriguingly, traditional multiple-input multiple-output (MIMO) communication methodologies, though effective in many contexts, confront stumbling blocks when applied to the unique intricacies of V2X communication. The paramount goal is to ensure that despite this spectral scarcity, communication remains both reliable and capable of accommodating the growing demands for high-capacity data exchange. This shift signifies a fundamental departure from conventional vehicular interactions, introducing a new era of interconnected and intelligent transportation systems [2].