基于改进Elmam神经网络的网络流量预测模型  

Prediction Model of Network Traffic Based on Modified Elman Neural Network

作　　者：王旭启[1] 赵宗涛[2] 

机构地区：[1]西京学院工程技术系,西安710123 [2]第二炮兵工程学院计算机系,西安710025

出　　处：《微计算机应用》2011年第12期24-28,共5页Microcomputer Applications

摘　　要：提出了一种改进Elman动态回归神经网络,在此基础上建立了一种网络流量预测模型,该模型相对于传统的线性模型和BP神经网络模型具有更高的预测精度和更好的自适应性,利用某大学校园网统计得到的实际网络流量数据进行仿真实验,结果表明该模型具有良好的预测效果。The modified Elman dynamic recurrent neural networks is proposed in this paper. Based on it, the network traffic prediction model is designed in this article. The model has higher precision and better adaptability than that of traditional linear model and BP neural network model. The perforanee of the proposed model is evaluted with the actual network traffic of an University schoolyard network. The experimental results show that the proposed model is effective and feasible.

关 键 词：Elmam 神经网络 网络流量 预测 模型 

分 类 号：TP393.06[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]