ML-Driven Resource Optimization in Active-Star-RIS-Aided THz ISAC Systems with DDA Modulation

This paper explores a cutting-edge terahertz (THz) integrated sensing and communication system (ISAC) that utilizes active simultaneously transmitting and reflecting reconfigurable intelligent surfaces (A-STAR-RIS). The system incorporates a novel dynamic delay alignment (DDA) modulation technique, allowing signals from different paths to reach the receiver simultaneously, eliminating the need for complex channel equalization and mitigating inter-symbol interference, while considering the dynamic movement of the vehicles, and accounting for time-selective fading and uniform Doppler power spectra (DPS) model. Our system features a dual-function radar and communication multiple antenna base station (BS), serving both communication and target sensing functions concurrently through an A-STAR-RIS. The objective is to maximize the sum rate by jointly optimizing BS transmit beamforming, A-STAR-RIS reflection and transmission beamforming matrices, vehicular unit (VU) mobility correlation parameters, and radar receive filter. Given the intricate nature of this non-convex optimization problem, owing to dynamic changes in communication links and the interplay of multiple variables, traditional optimization methods prove challenging. To overcome this, we propose a machine learning (ML) based deep deterministic policy gradient (DDPG) algorithm. Our simulations validate the substantial benefits of A-STAR-RIS over conventional benchmark scenarios.