Research and Prediction on Nonlinear Network Flow of Mobile Short Message Based on Neural Network

At present, research on nonlinear network flows of mobile short message is one hotspot in mobile communications fields. Nonlinear network flows of mobile short message have such essential features varying with time as periodicity, regularity, correlation, randomicity, occasionality. The traditional methods based on linear models are successful relatively in making irregular flow series become more regular, but compared with actual results, the forecasting results have more obvious deviations. According to real data measured, this paper has established a forecasting model of mobile short message network flows based on time series and improved bp algorithm, and used this model to research issues forecasting nonlinear network flows of mobile short messages. The experiment has shown that the forecasting model has higher precision and better extension compared with traditional models.