On Cost Minimization for Cache-Enabled D2D Networks with Recommendation

To accommodate the tremendous increase of mobile data traffic, cache-enabled device-to-device (D2D) communication has been taken as a promising technique to release the heavy burden of cellular networks since popular contents can be pre-fetched at user devices and shared among subscribers. As a result, cellular traffic can be offloaded and an enhanced system performance can be attainable. However, due to the limited cache capacity of mobile devices and the heterogeneous preferences among different users, the requested contents are most likely not be proactively cached, inducing lower cache hit ratio. Recommendation system, on the other hand, is able to reshape users' request schema, mitigating the heterogeneity to some extent, and hence it can boost the gain of edge caching. In this paper, the cost minimization problem for the social-aware cache-enabled D2D networks with recommendation consideration is investigated, taking into account the constraints on the cache capacity budget and the total number of recommended files per user, in which the contents are sharing between the users that trust each other. The minimization problem is an integer non-convex and non-linear programming, which is in general NP-hard. Therewith, we propose a time-efficient joint recommendation and caching decision scheme. Extensive simulation results show that the proposed scheme converges quickly and significantly reduces the average cost when compared with various benchmark strategies.