Popularity estimation in a popularity-based hybrid peer-to-peer network

The globally structured hybrid peer-to-peer systems combine structured and unstructured peer-to-peer networks where a structured ring based network forms the backbone of the system and multiple unstructured peer-to-peer networks are attached to this backbone. We show that if items are inserted into the system according to their popularity, search efficiency will be considerably improved. The key challenge in this scheme is how to identify rare items that should be inserted in the DHT. We analyze several approaches of identifying popularity of items in hybrid systems and propose an optimum approach for popularity estimation.