Proactive Computation Caching Policies For 5G-and-Beyond Mobile Edge Cloud Networks
Nicola di Pietro, Emilio Calvanese Strinati · 2018
Computation caching is a novel strategy to improve the performance and the quality of service of mobile edge cloud networks. It consists in storing in local memories situated at the edge of the network, here mobile access points, the already processed results of computations that users offload to the mobile edge cloud. The goal of this technique is to avoid redundant and repetitive processing of the same tasks, thus streamlining the offloading process and improving the exploitation of both users' and network's resources. In this paper, three different computation caching policies are proposed and evaluated. They are based on three main parameters: the popularity of offloadable tasks, the size of their inputs, and the size of their results. Numerical simulations show that good policies need to take into account these three parameters altogether.