In this work, we explore the use of active reconfigurable intelligent surfaces (A-RIS) to improve vehicle-to-everything (V2X) communication systems to address limitations in traditional vehicular communication. In particular, we formulate an optimization problem to maximize the uplink sum rate for vehicle-to-infrastructure (V2I) links by optimizing transmit precoders, phase-shift matrices, transmit power, and spectrum sharing for vehicle-to-vehicle (V2V) links. To handle complex hybrid control scenarios, we propose a mixed-action deep reinforcement learning (DRL) algorithm and compare it with conventional benchmark methods like deep deterministic policy gradient (DDPG) with discrete actions (DA) and alternating optimization (AO). We evaluate the proposed algorithm’s effectiveness under imperfect channel state information as well. Simulation results highlight the efficacy of our approach, demonstrating significant enhancement in vehicular communication quality through A-RIS. Furthermore, we illustrate the impact of various factors such as number of A-RIS elements, vehicle speed, loss, execution time, amplification power, and CSI error on the performance of the V2X system.
Enhancing V2X Communication with Active RIS: A MADRL Approach with Perfect and Imperfect CSI
07.10.2024
613543 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
MADRL-based UAVs Trajectory Design with Anti-Collision Mechanism in Vehicular Networks
ArXiv | 2024
|Cooperative Maneuvering Decision-Making of Multi-UAVs Based on MADRL-VD
Springer Verlag | 2024
|MADRL-based UAV swarm non-cooperative game under incomplete information
Elsevier | 2024
|