Popularity-aware dynamic clustering scheme for distributed caching in ICN
Mikiya Yoshida, Yusuke Ito, Yurino Sato, Hiroyuki Koga · 2022
To realize low-latency content delivery in Information-Centric Networking, a scheme to cluster domains and retain popular content in each cluster has been proposed, which enables consumers to retrieve content from nearby clusters. However, when the distribution of content popularity changes, all caches of content may not be retained adequately in a cluster, so consumers could not retrieve them from nearby clusters. We therefore propose a dynamic clustering scheme to adjust the cluster size, according to the change of content popularity, considering cache utilization and delivery latency, and evaluated its effectiveness through simulation.