A Short-term Combination Forecasting Model for Traffic Flow Based on the BP Neural Network

摘要

The forecasting for short-term traffic flow has always been one important and difficult research focus in the traffic forecasting areas. Based on the BP Neural Network, which was applied to nonlinear problems, the independent short-term forecasting models for the different traffic flow of the continuous time point series in one day and the constant date series at same time point were set up respectively, then, a short-term combination forecasting model for traffic flow, in which the regular fluctuations in the traffic flow data of the continuous time point series in one day and the constant date series at same time point were fully considered, was established, and can be applied to the complex spatio-temporal features of short-term traffic flow. With the sample of traffic flow dada, the forecasting results of the different models showed that the combination forecasting model provided a better forecast accuracy than the independent models.