Cache "less for more" in information-centric networks (extended version).

Abstract

Ubiquitous in-network caching is one of the key aspects of information-centric networking (ICN) which has received widespread research interest in recent years. In one of the key relevant proposals known as Content-Centric Networking (CCN), the premise is that leveraging in-network caching to store content in every node along the delivery path can enhance content delivery. We question such an indiscriminate universal caching strategy and investigate whether caching less can actually achieve more. More specifically, we study the problem of en route caching and investigate if caching in only a subset of nodes along the delivery path can achieve better performance in terms of cache and server hit rates. We first study the behavior of CCN's ubiquitous caching and observe that even naïve random caching at a single intermediate node along the delivery path can achieve similar and, under certain conditions, even better caching gain. Motivated by this, we propose a centrality-based caching algorithm by exploiting the concept of (ego network) betweenness centrality to improve the caching gain and eliminate the uncertainty in the performance of the simplistic random caching strategy. Our results suggest that our solution can consistently achieve better gain across both synthetic and real network topologies that have different structural properties. We further find that the effectiveness of our solution is correlated to the precise structure of the network topology whereby the scheme is effective in topologies that exhibit power law betweenness distribution (as in Internet AS and WWW networks).