On the performance analysis of distributed caching systems using a customizable Markov chain model

International audienceIn the last few years, Networks Operators (NO) have experienced an increased number of requests for video contents and rich media services, which are becoming increasingly popular. In view of the network scaling limitations, operators are developing their own caching systems to speed up the network performance. Indeed, disseminating caches in the infrastructure not only helps in absorbing the network's congestion, but in addition, brings content closer to users, which allows a reduced latency. Several studies have focused on improving the performance of such caching systems, especially in the context of Content-Centric Networking (CCN). In this paper, we propose a fairly generic model of caching systems that can be adapted very easily to represent different caching strategies, even the most advanced ones. Indeed, the proposed model of a single cache, named MACS, which stands for Markov chain-based Approximation of CCN Caching Systems, can be extended to represent an interconnection of caches under different schemes. In order to demonstrate the accuracy of our model, we proposed to derive the two most effective techniques in the literature, namely LCD and LRU-K, which may adapt to changing patterns of access. Simulation results using a discrete event simulator clearly show the accuracy of the proposed model under different network configurations