Efficient AoI-Aware Resource Management in VLC-V2X Networks via Multi-Agent RL Mechanism

Vehicles are already fitted with light-emitting diodes (LEDs), however, with a vehicles-to-everything (V2X) network, we can integrate this potential network of visible light communication (VLC). In this paper, we explore the problem of energy efficiency (EE) and age of information (AoI) aware in a cluster-based VLC V2X system. Through cellular wireless vehicle-to-everything (C-V2X) communication technology, vehicle clusters provide cooperative awareness messages (CAMs) to their members and communicate safety-critical messages to the roadside unit (RSU). The purpose of this study is to evaluate the impact of the rising number of vehicles on EE and AoI, as well as the effect of increasing the intra-cluster gap on AoI in order to maximize EE while minimizing AoI. To solve the EE problem involving quality of service (QoS) and power constraints, we employ the multi-agent reinforcement learning (MARL) mechanism. The simulations show an acceptable improvement in the system's performance.