Popularity-based partial caching for Information Centric Networks

Abstract

Information Centric Networking (ICN) is a proposal for a future network architecture that relies on in-network caching. While still an open problem, the default caching strategy in current ICN implementations is that routers cache everything that passes through them. It has been shown in previous work, that such a universal mode of caching is inefficient and highly redundant. In this work, we propose two popularity based caching schemes for Named Data Networking (NDN) that progressively cache file chunks as the file gets more popular. We compare our schemes with universal caching and other popularity based caching schemes and show that, for particular cache sizes, our schemes achieve higher cache hit rates, lower hop counts and hence, lower delivery delays. We also emulate content popularity dynamics on ndnSIM by simulating spatial and temporal locality of content items and study its effect on our popularity-based caching schemes.