Joint Active and Passive Beamforming for RIS Assisted ISAC Systems: A DRL Based Approach

Abstract

Integrated sensing and communication (ISAC) is regarded as a promising approach to alleviate spectrum congestion in future communication networks. Leveraging recent breakthroughs in programmable meta-materials, re-configurable intelligent surfaces (RIS) enhance communication systems by enabling multiple input multiple output (MIMO) transmission without requiring additional radio frequency (RF) chains. Therefore, integrating RIS into ISAC systems presents a promising solution to address the fundamental challenge of enhancing ISAC system performance through only active beamforming, especially in adverse channel conditions. This Study investigates the joint optimization of transmit beamforming and RIS reflection coefficients to maximize the sum capacity of ISAC systems. The study adopts a more practical approach by constraining each RIS element to use only a discrete set of phase shifts. Most contemporary works have used mathematical optimization tools to address the resulting non-convex optimization problem, leading to sub-optimal solutions. Thus, we address the non-convex optimization problem using the twin delayed deep deterministic (TD3) deep reinforcement learning (DRL) algorithm. Numerical results and analysis demonstrate improved sum capacity of the ISAC system using the suggested approach.