Cooperative Caching with Content Popularity Prediction for Mobile Edge Caching

Abstract

Mobile Edge Caching (MEC) can be exploited for reducing redundant data transmissions and improving content delivery performance in mobile networks. However, under the MEC architecture, dynamic user preference is challenging the delivery efficiency due to the imperfect match between users' demands and cached content. In this paper, we propose a learning-based cooperative content caching policy to predict the content popularity and cache the desired content proactively. We formulate the optimal cooperative content caching problem as a 0-1 integer programming for minimizing the average downloading latency. After using an artificial neural network to learn content popularity, we use a greedy algorithm for its approximate solution. Numerical results validate that the proposed policy can significantly increase content cache hit rate and reduce content delivery latency when compared with popular caching strategies.