Deep Reinforcement Learning to Improve Vehicle-to-Vulnerable Road User Communications in C-V2X

In this paper, we study the problem of optimizing the performance of vehicle-to-everything (V2X) using deep reinforcement learning techniques while sharing the spectrum between vehicle-to-infrastructure (V2I) links and vehicle-to-vulnerable road users (V2VRU) links in Cellular V2X (C-V2X). The objective is to protect VRU by improving the performance of V2VRU communications while maximizing the performance of V2I communications. Specifically, we formulate a spectrum sharing optimization problem with a two-objective function where the first objective is to improve the packet reception ratio (PRR) of VRU, whereas the second objective is to maximize the data rate of V2I communication links. To solve this challenging problem, we propose a deep reinforcement learning algorithm. A single agent controlling the vehicular network observes the environment and takes decisions accordingly by appropriately selecting the spectrum sub-bands and the transmission power levels. The simulation results show that the proposed scheme attains high performance compared to baseline solutions and solves the trade-off between maximizing the data rates of the vehicle users (V2I links) and improving the PRR of the V2VRU links.