Probabilistic Caching Mechanism Based on Software Defined Content Centric Network

Abstract

In-network caching is one of the core ideas of content centric network (CCN). The in-network caching strategy commonly used in CCN is inefficient, so a probabilistic caching mechanism SBPC based on software defined content centric network was proposed to efficiently utilize the whole network caching resource. SBPC uses controller to aware topology information and link state information in whole network, it quantify the importance of nodes according to their degree centrality, closeness centrality, betweenness centrality and eigenvector centrality. By means of matching node importance and content popularity, content is cached according to a probability caculated through node importance and content popularity. Simulation results show that SBPC can effectively increase the cache hit ratio, at the same time decrease the content acquisition hop and request delay compared with Lce, ProbCache, Prob(0.5) and Betw which are the traditional caching mechanisms in CCN.