Segment-Based Joint Caching and Recommendation Optimization for Mobile Video Transmission

Mobile edge caching is able to reduce transmission latency and relieve the traffic load of backhaul links in the delivery of mobile video contents. However, the content caching remains a challenging problem considering the relatively limited cache capacity and the heterogeneous user demand. Recommendation system, with the ability to shape users' demand, can be leveraged to improve the performance of mobile edge caching efficiency. In this paper, the caching policies and recommendation strategies are designed for the cache-enabled wireless networks. Considering popularity difference among segments in a single video content, a more fine-grained segment-based proactive caching policy is introduced, which is different from the existing works that focus on content-level caching. Besides, the impact of recommendation system on users’ request patterns is taken into account. In order to effectively reduce the content transmission latency, a joint caching and recommendation optimization problem is formulated. Due to the NP-hard nature, the problem is divided into two convex subproblems and a heuristic iterative algorithm is proposed. Numerical simulation results show that the proposed algorithm outperforms the existing algorithms in terms of both average transmission latency and cache hit ratio.