Scheduling Out-of-Coverage Vehicular Communications Using Reinforcement Learning

Performance of vehicle-to-vehicle (V2V) communications depends highly on the employed scheduling approach. While centralized network schedulers offer high V2V communication reliability, their operation is conventionally restricted to areas with full cellular coverage. In contrast, in out-of-cellular-coverage areas, comparatively inefficient distributed radio resource management used. To exploit benefits approach for enhancing reliability roads lacking coverage, we propose VRLS (Vehicular Reinforcement Learning Scheduler), a scheduler that proactively assigns resources out-of-coverage \textit{before} vehicles leave By training simulated vehicular environments, can learn policy robust and adaptable environmental changes, thus eliminating need targeted (re-)training complex real-life environments. We evaluate performance under varying mobility, load, wireless channel, configurations. outperforms state-of-the-art algorithm zones without coverage by reducing packet error rate half loaded conditions achieving near-maximum low-load scenarios.