RLAB: Reinforcement Learning-Based Adaptive Broadcasting for Vehicular Ad-Hoc Networks

Effective context-aware broadcasting of information to the areas of interest (AoI) is a challenging problem in vehicular ad-hoc networks. It is usually assumed that the information about these AoI is known a priori, either by a centralized source of information or by the entire set of vehicles. In this paper, we propose a self-adaptive broadcasting scheme based on distributed reinforcement learning, in which vehicles collaboratively tune the rate of their broadcasts based on the network dynamics without any initial knowledge about the geographical distribution of AoI. The proposed approach enables a more practical implementation of distributed context-aware broadcasting, which requires no global information and only partial synchronization. The convergence and broadcasting performance of the proposed learning system is evaluated using simulations for several setups. These results show a significant improvement, in terms of number of useful broadcasts and delay, over existing approaches, such as gossip-based broadcasting.