DIVER: A Diversity-Based Search-and-Routing Approach for Named-Data Networking
Ian Vilar Bastos, Igor M. Moraes · 2016
The Information-Centric Networking paradigm introduces a largely distributed in-network caching infrastructure. End-to-end routing and forwarding algorithms are no longer the most effective way to retrieve contents when volatile replicas are highly spread at network routers. Requests sent only towards servers that permanently store contents do not account for the possibility to retrieve volatile replicas stored at neighbours caches. Mechanisms that explore the network in order to search nearby replicas stored in cache can improve users experience and reduce network load. This paper proposes the Diversity-based Search-and- Routing (DIVER) mechanism to jointly work with traditional end-to-end routing algorithms. DIVER probes the network to find volatile content replicas and routers answer those probes by compressing its cached contents availability information in a space efficient data structure. To maximize content retrieval, DIVER keeps as much orthogonal as possible the contents membership in its interfaces. Simulation results show that DIVER reduces up to 87% the network load and 29% the distance to find volatile replicas when compared to a literature proposal.