Deep Reinforcement Learning-Based Joint Spectrum Allocation and Configuration Design for STAR-RIS-Assisted V2X Communications

Vehicle-to-everything (V2X) communications is pivotal for modern transportation systems, but the challenges arise in scenarios with buildings, leading to signal obstruction and limited coverage. To alleviate these challenges, reconfigurable intelligent surface (RIS) is regarded as an effective solution for communication performance by tuning passive signal reflection. RIS has acquired prominence in 6G networks due to its improved spectral efficiency, simple deployment, and cost-effectiveness. Nevertheless, conventional RIS solutions have coverage limitations. Researchers are exploring on the promising concept of simultaneously transmitting and reflecting RIS (STAR-RIS), which provides 360° coverage while utilizing the advantages of RIS technology. In this article, an STAR-RIS-assisted V2X communication system is investigated. An optimization problem is formulated to maximize the achievable data rate for vehicle-to-infrastructure (V2I) users while satisfying the latency and reliability requirements of vehicle-to-vehicle (V2V) pairs by jointly optimizing the spectrum allocation, amplitude and phase shift values of STAR-RIS elements, digital beamforming vectors for V2I links, and transmit power for V2V pairs. Since it is challenging to solve in polynomial time, we decompose our problem into two subproblems. For the first subproblem, we model the control variables as a Markov Decision Process and propose a combined double deep
$Q$
-network (DDQN) with an attention mechanism so that the model can potentially focus on relevant inputs. For the latter, a standard optimization-based approach is implemented to provide a real-time solution, reducing computational costs. Numerical results demonstrate that our solution approach outperforms the vanilla DDQN approach by 5.2%, and our proposed system outperforms the conventional RIS by 39%.