An On-demand Multi-Path Interest Forwarding strategy for content retrievals in CCN

Content Centric Networking (CCN) is a new paradigm in networking and a future Internet architecture. Performance evaluations show that conventional CCN forwarding strategies which use replication of Interests (standard) or the shortest path (best-face) do not perform well under high bandwidth requirements and loaded networks. We have designed and evaluated the performance of an On-demand Multi-Path Interest Forwarding (OMP-IF) strategy which identifies a set of paths based on the disjointness of paths to content locations. Then, the discovered paths are used simultaneously to distribute (split) Interests based on the characteristics of the paths. We have evaluated OMP-IF strategy using a simulator with a large scale network scenario and a realistic traffic generation model. The results show improved performance in CCN networks considering download time, load balancing, content hit ratios, and others.