Model of P2P traffic control based on neural networks

To improve the recognition accuracy and raise the detecting speed, a new model of P2P traffic control based on neural networks is proposed in this essay. The model is divided into several small-scale neural networks according to the characteristics of various existing types of P2P traffic, and every sub-neural network is divided into several smaller models in order to reduce the storage space and improve the detecting speed. The experiment results demonstrate that the new model indeed upgrades the detecting speed, reduces the misdeclaration rate and the omission rate, and to a great extent improves the recognition rate of new P2P traffic.