【作者】 戴悦；

【导师】 刘渊；

【作者基本信息】 江南大学 ， 计算机软件与理论， 2008， 硕士

【摘要】 随着Internet及其应用的迅速发展,网络规模日益增大,网络应用日益复杂,由于互联网是一个高度复杂的非线性系统,为了实现可靠的数据传输及合理的网络资源分配,就需要深刻了解网络的控制机制和复杂的行为特性。而网络流量预测是流量工程、拥塞控制和网络管理的核心问题。所以要进行准确的网络流量预测首先必须了解网络流量的特性。网络流量的非线性变化部分有混沌特性的存在这一观点已被证明。现有的网络流量研究方法只是单一采用线性或者非线性的方法进行处理,而忽略了对混沌特性的研究。本文针对网络流量的混沌特性,介绍网络流量的相空间重构方法和参数确认的方法,并通过简单的试验验证理论的可用性。同时将小波变换和非线性动力学方法相结合研究网络流量的混沌特性,并改进相空间重构方法。将混沌吸引子投影于小波滤波器向量所张的空间中,并充分利用了小波变换的去噪优点,将小波变换与相空间重构结合,构建出一个新的重构模型,并用试验证明其优越性。将小波神经网络混沌时间序列预测方法引入到网络流量预测中,给网络数据流的预测方法都提供了行之有效的新方法。更多还原

【Abstract】 As the rapid development and application of Internet, the scale of internet is becoming larger and larger, the application of the internet is becoming more and more complicated. Due to network is a very complicated non-line system, in order to realize reliable data transfer and reasonable internet resource distribution, it is very important to comprehend the control mechanism and complicated behavioral character of network.Distributed applications use predictions of network traffic to sustain their performance by adapting their behaviors. It’s important that we must firstly know the character of network traffic. It has been recognized that the network traffic of non-linear part has chaos characteristics. However, existent network traffic prediction study only utilize either linear or non-linear methods to solve the problem and neglect chaos characteristics.The paper bases on chaos characteristics introduce the way of phase space reconstrunction and parameter counting. And experimentalize to prove the theory.Bases on warelet transform and nonlinearity dynamics method to study chaos characteristics of network traffic flow, and improve phase space reconstrunction. Chaotic attractor was projected in the space of wavelet filter vector, and having fully utilized with warelet denoising. And prove the new method of network traffic prediction is advantage. Introduce the method of chastic time series predictior based on warelet neural network traffic flow prediction.And wavelet transform provide a affective new method of network traffic prediction.更多还原