Reconfigurable Intelligent Surface Enabled Vehicular Communication: Joint User Scheduling and Passive Beamforming

Given its ability to control and manipulate wireless environments, reconfigurable intelligent surface (RIS), also known as reflecting (IRS), has emerged a key enabler technology for the six-generation (6G) cellular networks. In meantime, vehicular environment radio propagation is negatively influenced by large set of objects that cause transmission distortion such high buildings. Therefore, this work devoted explore area RIS integration with communications while considering dynamic nature communication environment. Specifically, we provide system model where RoadSide Unit (RSU) leverages indirect transmissions disconnected areas, dark zones. Dark zones are spots within RSU coverage links blocked due existence blockages. details, discrete utilized between vehicles passing through out-of-service joint problem resource scheduling passive beamforming or phase-shift matrix formulated an optimization objective maximizing minimum average bit rate. The mixed integer non-convex program which difficult be solved does not account uncertain in Thereby, resort alternative methods based on Deep Reinforcement Learning determine Block Coordinate Descent (BCD) solve matrix, i.e., beamforming, RIS. Markov Decision Process (MDP) defined complexity solution approach discussed. Our numerical results demonstrate superiority our proposed over baseline techniques.