An Empirical Research on Telecommunication Traffic Forecasting Based on Chaos Theory

Forecasting of Telecom Traffic influence directly the future development of telecommunications enterprises. According to the complexity and non-linearity of Telecom Traffic , in this paper, the hybrid of wavelet transform (WT), chaos and SVM model was established. First the chaotic feature of Telecom Traffic is verified with chaos theory. It can be seen that Telecom Traffic possessed chaotic features, providing a basis for performing short-term forecast of Telecom Traffic with the help of chaos theory. The original time series is decomposed by wavelet transform to eliminate the instability. Then Average Mutual Information (AMI) method is used to find the optimal time lag of Every single decomposed series. Cao´s method is adopted to determine free parameters of support vector machines. Additionally, the proposed model and SVM model were tested on the prediction of Telecom Traffic of Chongqing province Telecommunications operator in China to prove the model´s validity.