An Edge Caching Strategy Based on Long-Term and Short-Term Interests Reshaping of Users

In the context of edge caching, the prevalent challenges of unknown user preferences and high heterogeneity significantly hinder the performance of caching systems. To address these issues, this paper proposes an edge caching strategy based on reshaping users' long-term and short-term interests. Firstly, we establish a basic click-through rate prediction model and introduce automated and adaptive search algorithms to obtain optimal short-term interests durations and high-quality long-term interests feature representations through end-to-end optimization. Then, we design a dynamic recommendation mechanism based on user preferences, reshaping the content request probabilities of different users to influence caching decisions. Finally, we formulate a joint problem of maximizing system utility by integrating diverse edge caching and user recommendations, decoupled into a caching sub-problem and a recommendation sub-problem. These are solved using a regional greedy algorithm and a one-to-one exchange matching algorithm, respectively, and iterative updates are performed to achieve convergent optimization results. Simulation results show that the proposed algorithm effectively improves caching performance.