SMBSRP: a search mechanism based on interest similarity, query relevance and distance prediction
IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I
| Hi-index | 0.00 |
The search width and search depth is the key factor of unstructured Peer-to-Peer (P2P) network search algorithms in unstructured Peer-to-Peer (P2P) network. Existing guided search algorithms decreased search width by QoS or history search records, the TTL (time to live) can be used to constrain the search depth. However, there is a huge difference in the number of nodes searched by TTL-based algorithm even with the same search depth. And each search branch of the TTL-based algorithm can only search the same depth of the network, thus resulting in the unstable search efficiency. In this paper, a controllable cost search algorithms is presented, which would ensure more stable number of search nodes and achieve different search branches using different search depth, Experiments show that ours search algorithm based on budget in unstructured P2P network has more stable number of searched nodes, and greatly improved the utilization rate of search message, the successful rate of search and the search efficiency.