Enhanced Proactive Caching Through Content Recommendation

The mismatch between user demand and service supply creates a congestion in mobile wireless networks. Taking advantage of user demand predictability, Service Providers (SPs) apply proactive caching to smooth out the network load. However, the performance of applied caching strategy depends on the content popularity information. This paper studies the effect of recommendation on empowering the caching performance. We exploit the presence of recommendation as an interacting tool between the user and the small Base Station (sBS), to reduce the uncertainty about user demand. Building upon the fact that recommendation reshapes the user demand, we develop a user request model at which his demand is affected by the applied recommendation. Simulations reveal the superiority of our proposed approach compared to the state-of-the-art method.