Gain-Aware Caching Scheme Based on Popularity Monitoring in Information-Centric Networking

Long CHEN  Hongbo TANG  Xingguo LUO  Yi BAI  Zhen ZHANG  

IEICE TRANSACTIONS on Communications   Vol.E99-B   No.11   pp.2351-2360
Publication Date: 2016/11/01
Publicized: 2016/05/19
Online ISSN: 1745-1345
DOI: 10.1587/transcom.2015EBP3539
Type of Manuscript: PAPER
Category: Network
information-centric networking,  in-network caching,  content placement,  chunk-level popularity monitoring,  

Full Text: PDF(1.8MB)>>
Buy this Article

To efficiently utilize storage resources, the in-network caching system of Information-Centric Networking has to deal with the popularity of huge content chunks which could cause large memory consumption. This paper presents a Popularity Monitoring based Gain-aware caching scheme, called PMG, which is an integrated design of cache placement and popularity monitoring. In PMG, by taking into account both the chunk popularity and the consumption saving of single cache hit, the cache placement process is transformed into a weighted popularity comparison, while the chunks with high cache gain are placed on the node closer to the content consumer. A Bloom Filter based sliding window algorithm, which is self-adaptive to the dynamic request rate, is proposed to capture the chunks with higher caching gain by Inter-Reference Gap (IRG) detection. Analysis shows that PMG can drastically reduce the memory consumption of popularity monitoring, and the simulation results confirm that our scheme can achieve popularity based cache placement and get better performance in terms of bandwidth saving and cache hit ratio when content popularity changes dynamically.