Reinforcement learning-driven vehicular content caching

In-network caching can shorten the distances between consumers and contents. Therefore, we leverage in-network caching to enable vehicles to rapidly access vehicular contents such as road conditions, thereby giving vehicles sufficient time to correctly handle potential road hazards ahead. We propose a reinforcement learning-driven vehicular content caching method aimed at suppressing caching failures caused by vehicle mobility and insufficient resources, while achieving the objective of shortening distances between vehicle consumers and vehicular contents. The proposed method leverages reinforcement learning to mitigate the effects of vehicle mobility on content caching and improve the success rates of content caching. Furthermore, vehicle resources and content features are exploited to make content caching decisions, ensuring that vehicles with richer resources can cache contents with longer lifetimes. The experimental results demonstrate the superiority of the proposed method in terms of caching success rates and hop count between vehicles and cached data.