一种基于差分进化的BP神经网络学习算法  

A novel learning algorithm of BP neural network based on differential evolution

作　　者：王晓敏[1] 刘宏伟[1] 李石妍[1] 

机构地区：[1]河北工程大学机电工程学院,河北邯郸056038

出　　处：《电子设计工程》2011年第15期16-18,共3页Electronic Design Engineering

摘　　要：提出了一种基于改进差分进化算法和BP神经网络的计算机网络流量预测方法。利用差分进化算法的全局寻优能力,快速地得到BP神经网络的权值和阈值;然后利用BP神经网络的非线性拟合能力获得高精度的网络流量预测结果。实验结果表明,此方法能在较短的时间内获得较高精度的预测结果,具有较好的应用价值。A novel method based on improved differential evolution algorithm and BP neural networks for computer network traffic prediction was proposed.The weight values and threshold values of BP neural network were obtained speedy by using the global optimization ability of differential evolution algorithm,and then the good prediction accuracy of network traffic was achieved by using nonlinear fitting ability of BP neural network.The experiments results show that the proposed method can obtain good prediction accuracy of network traffic with low cost of time relatively,and has the advantages of good application value.

关 键 词：差分进化 学习算法 BP神经网络 网站流量预测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]