相空间重构和正则极限学习机的网络流量预测

发布时间：2018-06-17 17:31

本文选题：网络流量 + 正则极限学习机　；参考：《激光杂志》2015年01期

【摘要】：网络流量预测一直是网络研究技术中的热点,针对网络流量变化的时变性、混沌性,提出一种相空间重构和正则极限学习机的网络流量预测模型。首先收集大量的网络流量历史样本,并进行相应的预处理,然后根据混沌理论确定最优延迟时间和嵌入维数,并重构网络流量学习样本,最后采用正则极限学习机建立网络流量预测模型,并进行仿真对比实验。结果表明,相对于其它网络流量预测模型,本文模型可以更加准确描述网络流量的非线性变化特点,提高网络流量预测精度,预测结果具有一定实用价值。
[Abstract]:Network traffic prediction has always been a hot topic in network research technology. Aiming at the time-varying and chaotic nature of network traffic change, a network traffic prediction model based on phase space reconstruction and regular limit learning machine is proposed. Firstly, a large number of network traffic history samples are collected, then the optimal delay time and embedding dimension are determined according to chaos theory, and the network traffic learning samples are reconstructed. Finally, the network traffic prediction model is established by using the regular limit learning machine, and the simulation results are compared. The results show that compared with other network traffic prediction models, this model can more accurately describe the nonlinear characteristics of network traffic, improve the accuracy of network traffic prediction, and the prediction results have certain practical value.
【作者单位】：常熟理工学院电气与自动化工程学院;
【分类号】：TP393.06

【相似文献】