电子设计工程
電子設計工程
전자설계공정
ELECTRONIC DESIGN ENGINEERING
2011年
15期
16-18
,共3页
差分进化%学习算法%BP神经网络%网站流量预测
差分進化%學習算法%BP神經網絡%網站流量預測
차분진화%학습산법%BP신경망락%망참류량예측
differential evolution%learning algorithm%BP neural network%website traffic prediction
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。
提齣瞭一種基于改進差分進化算法和BP神經網絡的計算機網絡流量預測方法。利用差分進化算法的全跼尋優能力,快速地得到BP神經網絡的權值和閾值;然後利用BP神經網絡的非線性擬閤能力穫得高精度的網絡流量預測結果。實驗結果錶明,此方法能在較短的時間內穫得較高精度的預測結果,具有較好的應用價值。
제출료일충기우개진차분진화산법화BP신경망락적계산궤망락류량예측방법。이용차분진화산법적전국심우능력,쾌속지득도BP신경망락적권치화역치;연후이용BP신경망락적비선성의합능력획득고정도적망락류량예측결과。실험결과표명,차방법능재교단적시간내획득교고정도적예측결과,구유교호적응용개치。
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.
