Caching Strategy Based on Hierarchical Cluster for Named Data Networking

The in-network caching strategy in named data networking can not only reduce the unnecessary fetching of content from the original content server deep in the core network and improve the user response time, but also ease the traffic in the core network. However, challenges exist in in-network caching, such as the distributed locations of storage and relatively small cache space which limit the hit rate, and the cache management introduces further overhead. In this paper, we propose a two-layer hierarchical cluster-based caching solution to improve in-network caching efficiency. A network is grouped into several clusters, then, a clusterhead is nominated for each cluster to make caching decision. The clustering approach offers scalability and permits multiple aspects of inputs to be used for decision making. Our solution jointly considers the location and content popularity for caching. We implement our strategy in ndnSIM and test it on GEANT-based network and AS3967 network. Our simulation results show significant improvement over its peers.