Reinforcement learning for 5G caching with dynamic cost

In next generation cellular networks (5G) the access points (APs) are anticipated to be equipped with storage devices to serve locally requests for reusable popular contents by caching them at the edge of the network. The ultimate goal is to shift part of the load on the back-haul links from on-peak to off-peak periods, contributing to a better overall network performance and service experience. In order to enable the APs with efficient (optimal) fetch-cache decision making schemes able to work in dynamic settings, we introduce simple but flexible generic time-varying fetching and caching costs, which are then used to formulate a constrained minimization of the aggregate cost across files and time. Since caching decisions in every time slot influence the content availability in future instants, the novel formulation for optimal fetch-cache decisions falls into the class of dynamic programming, for which efficient reinforcement-learning-based solvers are proposed. The performance of our algorithms is assessed via numerical tests, and discussions on the inherent fetching-versus-caching trade-off are provided.