Joint Optimization for Social Content Delivery in Wireless Networks

Over the past decade, success of social networks has significantly reshaped how people consume information. Recommendation of contents based on user profiles is well received. However, as users become dominantly mobile in content consumption, little is done to consider the optimization regarding the wireless environment. In this paper, we investigate a centralized wireless content delivery system with heterogeneous base stations, aiming to optimize overall user rewards given the capacity constraints of the wireless networks. We propose a scheduling framework incorporating content deliverability.  Results indicate this novel joint optimization approach outperforms existing systems, which separates recommendation and delivery, especially when the wireless network is operating at maximum capacity.