基于径向基函数神经网络的网络流量识别模型

提出了一种基于径向基函数神经网络的网络流量识别方法。根据实际网络中的流量数据,建立了一个基于RBF神经网络的流量识别模型。先介绍了RBF神经网络的结构设计及学习算法,针对RBF神经网络在隐节点过多的情况下算法过于复杂的缺点,采用了优化的算法计算隐含层节点。仿真实验证明,该模型具有较好的准确率、低复杂度、高识别效果和良好的自适应性。

Modeling network traffic based on radial basis function nerual network

This paper presents a method of network traffic identification based on RBF(Radial Basis Function) neural network.With a large amount of real traffic data collected from the actual network,a nonlinear network traffic model based on radial basis function neural network theory was constructed to identify the network traffic.Firstly present the structure design and leaning algorithm of RBF neural network and then in order to reduce the artificial complexity of the RBF when too many hide layer units,present an optimize algorithm to calculate the numbers of hide layer units.Finally prove this identification method in the application of network traffic has the characteristics of high accuracy,low complexity and high recognition efficiency,and the practical feasibility in real-time traffic identification.