The short-term prediction of the mobile communication traffic based on the product seasonal model

Abstract

The short-term forecast can be used to respond to the unexpected business shocks in advance, thus guaranteeing user experience. We present a practical communication traffic forecasting technology based on autoregressive moving average model. The proposed short-term prediction method is mainly based on the product seasonal model. The orders of product seasonal ARMA equation are recognized by the Akaike information criterion, and the parameters of equation are estimated by the maximum likelihood method. The unit root test is used to judge the stability and reversibility of the model. The performance of the proposed method is evaluated. The experimental result shows that the method has high prediction accuracy. The short-term forecast can provide a basis for mobile operators to accurately expand capacity.