DRL-Based Phase Optimization for O-RIS in Dual-Hop Hard-Switching FSO/RIS-aided RF and UWOC Systems
This work addresses the challenge of reliable and high-capacity communication in 6G cross-domain underwater wireless optical networks, representing an incremental advancement by applying existing DRL methods to a new hybrid system.
The paper tackled the problem of optimizing phase shifts in a dual-hop hybrid communication system for 6G networks, using deep reinforcement learning (DRL) algorithms like DDPG and TD3, and demonstrated substantial improvements in outage probability and channel capacity, with TD3 showing superior robustness and adaptability.
This paper presents a dual-hop hybrid framework that integrates a free-space optical (FSO)/RIS-aided radio frequency (RF) link operating under a hard-switching protocol as the first hop, and an optical reconfigurable intelligent surface (O-RIS)-assisted underwater wireless optical communication (UWOC) link as the second hop. To capture realistic underwater dynamics, the Oceanic Turbulence Optical Power Spectrum (OTOPS) is employed for accurate turbulence modeling. For efficient O-RIS phase control, deep reinforcement learning (DRL) algorithms, specifically the Deep Deterministic Policy Gradient (DDPG) and Twin Delayed DDPG (TD3), have been developed to optimize the phase shifts of O-RIS elements. Simulation results demonstrate that the proposed system substantially improves outage probability and channel capacity, with TD3 achieving superior robustness and adaptability. These findings highlight the DRL-enabled O-RIS as a promising approach for achieving reliable and high-capacity 6G cross-domain UWOC networks.