With the rapid development of Internet of vehicles (IoV) and the continuous emergence of vehicle information applications, the demand for content in vehicle networking is growing at an alarming speed. Mobile vehicular edge caching is regarded as a promising technology in improving Quality of Service (QoS) and reducing latency. Many caching algorithms have been proposed, which usually place contents in the Road Side Units (RSUs) to provide services to users near them. However, due to the high-speed movement of vehicles and limitations of RSU coverage, caching interrupts often occur frequently, leading to a deterioration in service quality. To deal with this problem, we make full use of Vehicle-to-Vehicle (V2V) collaboration to construct a caching system which does not require RSU support, and propose a Recursive Deep Reinforcement Learning based Collaborative Caching Relay strategy (RDRL-CR). On purpose to minimize the service delay under capacity constraints, the caching problem is formulated as an integer linear programming problem, and caching decisions are achieved through partially observable Markov Decision Process (MDP). Specifically, this strategy utilizes a Graph Neural Network (GNN) to predict vehicle trajectories, and then selects vehicles that can serve as caching nodes by calculating link stability metrics between vehicles. The Long Short Term Memory (LSTM) network is embedded into a deep deterministic strategy gradient algorithm to achieve the final caching decision. Compared with existing caching strategies, the proposed caching strategy in this paper improves the caching hit rate by about 25% and reduces content access latency by about 20%.

Considering scenarios without road side unit coverage,a recursive deep reinforcement learning-based collab-orative caching relay algorithm was proposed to construct a caching system by leveraging the cooperation among ve-hicles.Recognizing the dynamic nature of caching decisions,the problem was modeled as a partially observable Markov decision process.Vehicle trajectories were predicted using graph neural network,and the connectivity stability between vehicles was measured to select those that could serve as caching nodes.In addition,long short-term memory network was integrated into the deep deterministic policy gradient algorithm to achieve the final caching decision.Simulation re-sults demonstrate that the proposed algorithm outperforms traditional caching algorithms in terms of cache hit ratio and latency.

The rapid growth of the Internet of Vehicles (IoV) and the increasing use of vehicle information applications has led to the recognition of mobile vehicular edge caching as a viable technology that can improve Quality of Service (QoS) and reduce latency. Numerous caching algorithms have been suggested, with the common approach being the storage of contents in Road Side Units (RSUs) as a way to offer service to users in proximity. However, the high-speed movement of vehicles and limited coverage of RSUs frequently result in caching interrupts, which lead to a decline in service quality. In response, we maximise Vehicle-to-Vehicle (V2V) collaboration to create a caching system that operates without RSU support. We introduce a Recursive Deep Reinforcement Learning Collaborative Caching Relay strategy (RDRL-CR) to address this problem. With the aim of reducing service delay within capacity constraints, the caching problem is converted into a linear programming problem, with caching decisions being made through a partially observable Markov Decision Process (MDP). This approach employs a Graph Neural Network (GNN) to predict vehicle trajectories, before selecting vehicles that can act as caching nodes using link stability metrics between them. The LSTM network has been incorporated into a deep deterministic policy gradient algorithm with the aim of achieving the ultimate caching decision.