基于小波支持向量机的VBR视频流量预测

：VBR视频流量具有时变性、突发性和非线性等变化特点，为了提高VBR视频流量的预测精度，提出一种小波支持向量机的VBR视频流量预测模型(WSVM)。首先对VBR视频流量时间序列进行相空间重构，然后将其输入到小波支持向量机进行学习，建立VBR视频流量预测模型，最后采用仿真实验对模型性能进行测试，并与支持向量机、小波神经网络进行对比。仿真结果表明，相对于其它预测模型，WSVM模型提高了VBR视频流量预测精度，能够更加准确反映VBR视频流量的复杂变化规律。

VBR video traffic prediction based on wavelet support vector machine

VBR video traffic has time-varying and nonlinear characteristics, in order to improve the prediction accuracy of VBR video traffic, this paper presents video traffic prediction model based on wavelet support vector machine (WSVM). Firstly, VBR video traffic time series is reconstructed by the phase space reconstruction and then are input into t WSVM to learn and build the prediction models of VBR video traffic, finally the simulation experiment is carried out to test the performance of the model. The simulation results show that, compared with support vector machine and wavelet neural network, WSVM has improved the prediction accuracy of VBR video traffic, and it can more accurately reflect the complex variation of VBR video traffic.