Algorithm of P2P Data Flow Clustering
ZHU Lizhi
Abstract：P2P technology is one of the fastest network technology development today ,but a large number of P2P data flow causes some impact to internet ,so in order to control the adverse impact of P2P traffic generated by the internet ,it is necessary to identify and classify P2P and non-P2P traffic flow .However ,the data flow clustering is an important step to study dataflow of different properties ,a P2P data flow clustering algorithm is proposed based on network traffic behavior characteristics ,thinking of the algorithm is :first description of P2P traffic packets features ,according to the characteristics of P2P packets using similarity calculation algorithm similar to P2P flow calculations ,followed by the use of decision tree al-gorithm for P2P and non-P2P data flow classification ,and finally the use of Euclidean distance and PSO similar P2P flow cluster .
Keywords：P2P flowparticle swarmsimilarityEuclidean distancedecision trees
Publication Date：2016-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1416-1419,1517 )