Hierarchical Clustering of Peers based on Properties for Unstructured P2P Systems
Michael Angelo G. Salvo, Romeo Mark A. Mateo, Jae-Wan Lee · 한국인터넷정보학회 학술발표대회 논문집 · 2008
In unstructured peer-to-peer (P2P) systems, file placement is random and no correlation exists between peers and their contents. Flooding queries does not guarantee the location of desired data. In this paper, we propose to cluster nodes in unstructured P2P systems using the agglomerative hierarchical clustering algorithm to improve the search method. We compare the delay time of clustering nodes between our proposed algorithm and the k-means clustering algorithm. Simulation was also done to determine the delay time of locating data in a topology using our proposed algorithm, k-means clustering, and without clustering. We find that the delay time of our proposed algorithm is shorter compared to other methods.