Abstract: In order to improve the prediction accuracy of network traffic, a novel prediction traffic method is proposed. In this model, wavelet transform is used to network decomposition at first, and each component is predicted by Support Vector Machine（SVM）, so as to reconstruct the prediction results. Then, the simulation is conducted to study on the different prediction model. The results show that this model has good performance, and the prediction accuracy is 6.347.

Key words: combination prediction model, wavelet decomposition and reconstruction, Support Vector Machine（SVM） model, αTrous algorithm

摘要： In order to improve the prediction accuracy of network traffic, a novel prediction traffic method is proposed. In this model, wavelet transform is used to network decomposition at first, and each component is predicted by Support Vector Machine（SVM）, so as to reconstruct the prediction results. Then, the simulation is conducted to study on the different prediction model. The results show that this model has good performance, and the prediction accuracy is 6.347.

关键词: combination prediction model, wavelet decomposition and reconstruction, Support Vector Machine（SVM） model, αTrous algorithm