摘要： 根据实际网络中测量得到的网络流量数据，建立一个基于Elman神经网络的流量模型，介绍Elman神经网络的架构设计，并提出一种基于正交最小二乘的学习算法，在此基础上对网络流量进行预测。仿真实验结果表明，该模型具有良好的预测效果，相对于传统线性模型及BP神经网络模型具有更高的预测精度和更好的自适应性。

关键词: Elman神经网络, 网络流量, 建模, 预测

Abstract: With a large amount of network traffic data collected from the actual network, a network traffic model based on Elman neural network theory is constructed. The structure design of Elman neural network is introduced, and a leaning algorithm based on orthogonal least squares is proposed, on basis of which, the network traffic is predicted. Simulation experimental results show this model has better effect of prediction, and compared with traditional linear model and BP neural network model, it has higher precision and better adaptability.

Key words: Elman neural network, network traffic, modeling, prediction

中图分类号: 

• TP393.02