A support vector machine neural network is proposed for performing VBR video traffic prediction.It takes differential signal as the input of the network.According to the criteria of structural risk minimization of SVM

the errors between sample-data and model-data are minimized and the upper bound of predicting error of the model is also decreased simultaneously so that the ability of generalization of the model is much improved.The simulation results show that the prediction error of SVM neural networks is 0.0018

while the prediction error of GRBF neural networks is 0.0029.In prediction precision

SVM neural networks model extended 40% than GRBF model.