Towards Efficient and Lightweight Collaborative In-Network Caching for Content Centric Networks

Abstract

In-network content caching is an inherent capability of Content Centric Networking (CCN) architecture. Undoubtedly, efficient caching strategies can help CCN networks to achieve high performance content dissemination. In general, there are two types of caching strategies: collaborative and non-collaborative caching strategies. Compared with non-collaborative caching strategies, collaborative caching strategies have much better caching performance. However, collaborative caching strategies incur extra overhead (e.g., computation and communication). To make a trade-off between the performance and overhead, we propose a distributed lightweight collaborative in-network caching strategy in this paper, called Popularity Publishing based caching strategy (PopPub for short). PopPub uses a lightweight protocol to publish the content popularity statistics counted by edge routers to other routers, and caches different contents at different routers along the content delivery paths based on the popularities of the contents. To evaluate the performance of PopPub, we conduct both theoretical analysis and extensive simulations on different topologies. The evaluation results confirm that PopPub yields the best performance compared with several state-of-art caching strategies, and the extra overhead incurred by PopPub is low.