Study on P2P Network Flow Recognition Algorithm Based on Machine Learning
YUAN Huabing
Abstract：In order to improve the accuracy of P2P network traffic recognition,this paper uses the dragonfly algorithm to opti?mize the weight and threshold of Elman neural network. A P2P network traffic recognition model based on DA-Elman machine learn?ing is proposed. The five characteristic attributes of the TCP traffic ratio,the number of connections to different IP numbers,the av?erage packet length,the uplink traffic ratio,and the total number of packets are used as inputs to the DA-Elman model,and the network traffic type is used as the DA-Elman output. Compared with PSO-Elman,GA-Elman,and Elman,the research results show that DA-Elman can effectively improve the accuracy of P2P network traffic recognition,with an accuracy rate of 98.4252%, providing new methods and approaches for P2P network traffic identification.
Keywords：machine learningElman neural networkparticle swarm optimization algorithmgenetic algorithmnetwork traffic recognition
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 2387-2391 )