High-Resolution Traffic Flow Prediction Model Based on Deep Learning

The time resolution of the existing traffic flow prediction model is too big to be applied to adaptive signal timing optimization.Based on the view of the platoon dispersion model,the relationship between vehicle arrival at the downstream intersection and vehicle departure from the upstream intersection was analyzed.Then,a high-resolution traffic flow prediction model based on deep learning was developed.The departure flow rate from the upstream and the arrival flow rate at the downstream intersection was taking as the input and output in the proposed model,respectively.Finally,the parameters of the proposed model were trained by the field data,and the proposed model was implemented to forecast the arrival flow rate of the downstream intersection.Results show that the proposed model can better capture the fluctuant traffic flow and reduced MAE,MRE,and RMSE by 9.53%,39.92%,and 3.56%,respectively,compared with traditional models and algorithms,such as Robert­son's model and artificial neural network.Therefore,the proposed model can be applied for realtime adaptive signal timing optimization.