Cooperative Content Caching and Delivery in Vehicular Networks: A Deep Neural Network Approach

The growing demand for low delay vehicu-lar content has put tremendous strain on the backbone network. As a promising alternative, cooperative con-tent caching among different cache nodes can reduce content access delay. However, heterogeneous cache nodes have different communication modes and lim-ited caching capacities. In addition, the high mobil-ity of vehicles renders the more complicated caching environment. Therefore, performing efficient cooper-ative caching becomes a key issue. In this paper, we propose a cross-tier cooperative caching architecture for all contents, which allows the distributed cache nodes to cooperate. Then, we devise the communica-tion link and content caching model to facilitate timely content delivery. Aiming at minimizing transmission delay and cache cost, an optimization problem is for-mulated. Furthermore, we use a multi-agent deep rein-forcement learning (MADRL) approach to model the decision-making process for caching among heteroge-neous cache nodes, where each agent interacts with the environment collectively, receives observations yet a common reward, and learns its own optimal policy. Extensive simulations validate that the MADRL ap- proach can enhance hit ratio while reducing transmis-sion delay and cache cost.