Mode Decomposition Based Hybrid Model for Traffic Flow Prediction

Traffic flow prediction plays a vital role in the real-time control of intelligent transportation system. A number of prediction models are established and achieve good results. However, most of these models ignore the intrinsic characteristics of traffic flow data, which can hardly optimize prediction models accordingly. This paper analyzes the characteristics of traffic flow time series and proposes a mode decomposition based hybrid model for traffic prediction. Firstly, the original sequence is decomposed by a mode decomposition algorithm, and the periodic sequence and two-part random sequences are obtained. Then, according to the complexity of decomposed subsequences, a hybrid prediction model with BP, ε-SVR and LSTM models is established to predict decomposed subsequences respectively. Finally, the final result is obtained by combining the prediction results of decomposed subsequences. Considering practical application scenario, the proposed model chooses to predict multi-prediction intervals instead of only predicting one single interval, but the predication flow data is still updated in accordance with one interval. The dataset from Caltrans Performance Measurement System is used in experiments. Comparing with typical single predicting models, experiment results show that the proposed hybrid model achieves higher accuracy.