A Hopfield Neural Network Flow Classifier in IP Switching

Download PDF
Open Webpage

Lianyuan Li, Zemin Liu, Zheng Zhou

Published: 2000, Last Modified: 07 Jan 2026IJCNN (5) 2000EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Flow classification in an IP switch is discussed. Different traditional flow classifiers are briefly introduced. Then a Hopfield neural network flow classifier (HNNC) is proposed. It can detect services as suitable for switching in accordance with the virtual circuit space of the IP switch. The simulation results show that services suitable to be switched are detected by HNNC and the majority of packets are assigned to a minimum number of flows.