Research on Multi-step Prediction of the Short-Term Information by Empirical Model Decomposition to Abnormal State Road Traffic Information

Abstract

For the characteristics of road traffic information under the abnormal state, in this paper empirical mode decomposition method is selected for nonlinear decomposition, design the short-term prediction method of traffic flow parameters based on empirical mode decomposition (EMD), classify and recombinant the traffic flow parameters based on the fluctuation frequency, by using Gray theory model, Kalman filtering method and autoregressive moving average method to predict the traffic flow parameters, the combination forecasting model can overcome the large volatility characteristics of the road traffic information under abnormal state, get the predictive value of real-time traffic data, then assign weights with the historical traffic parameters data, use Multi-step prediction to get the final traffic parameters forecast results. The results show that the method has a high prediction accuracy, lay a solid foundation for further research.