BGCC: a Bloom Filter-based Grouped-Chunk Caching Approach for Information-Centric Networking

Abstract

Packet-level caching is difficult to implement in the traditional caching system. The emergence of Information-centric networking (ICN) has alleviated this problem. However, the chunklevel caching is still facing severe scalability issues. In this paper, we analyze the issues which limit the implementation of chunk-level caching and propose a chunk-level caching optimization approach called BGCC. In BGCC, we reduce the consumption of fast memory by creating the index with group prefixes instead of the chunk prefixes, while the group-level popularity is also used to optimize caching decision. We evaluate the performance of our scheme through extensive simulation experiments regarding a wide range of performance metrics. The experimental results indicate BGCC can reduce the fast memory usage and achieve significant improvement in terms of server load reduction ratio, average hop reduction ratio and average cache hit ratio, compared with current chunk-level caching schemes.