Context-Aware Proactive Content Caching with Service Differentiation in Wireless Networks

Content caching in small base stations (SBSs) or wireless infostations is considered as a suitable approach to improve the efficiency in wireless content delivery. Due to storage limitations, placing the optimal content into local caches is crucial. Cache content placement is challenging since it requires knowledge about the content popularity distribution, which is often not available in advance. Moreover, content popularity is subject to fluctuations as mobile users with different interests connect to the caching entity over time. In this paper, we propose a novel algorithm for context-aware proactive cache content placement. By regularly observing context information of connected users, updating the cache content accordingly and observing the demands for cache content subsequently, the algorithm learns context-specific content popularity online over time. We derive a sub-linear regret bound, which characterizes the learning speed and proves that our algorithm asymptotically maximizes the average number of cache hits. Furthermore, our algorithm supports service differentiation by allowing operators of caching entities to prioritize groups of customers. Our numerical results confirm that by exploiting contextual information, our algorithm outperforms state-of-the-art algorithms in a real world data set, with an increase in the number of cache hits of at least 14%.