摘要
提出了一种结合分形滤波与线性神经网络进行网络流量预测的新方法。通过分形滤波增强网络流量中的长相关结构,使序列更加平滑,根据相空间重构理论利用线性神经网络进行预测操作,并用实际网络流量验证该模型的有效性。
This article proposes a new method to model and predict network traffic based on fractal filter and linear neural network.A smoothing series can be generated after increasing the long-range dependence in the time series by fraetal filter,according to the theory of phase space restructure,the linear neural network model is constructed,experiments of real network traffic illustrate that the prediction results using the method are better than the traditional models.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第3期124-126,共3页
Computer Engineering and Applications
基金
国家自然科学基金(No.60674054)~~
关键词
分形
自相似
神经网络
分形滤波
网络流量
fractal
self-similarity
neural network
fractal filter
network flow