出版社：Canadian Research & Development Center of Sciences and Cultures
摘要：The prediction of short-term traffic flow has become one of the core researched content of ITS, and plays a key role in traffic management and control. Considering the concept of time varying parameters and the volatility of traffic flow data, multi-level recursive method based on PGAGO(Generalized Accumulated Generating Operation) GM (1,1) is adopted in this paper to improve the accuracy of the prediction and make the prediction model more tally with the actual situation. The forecast step is divided into two parts: the prediction of model parameters and traffic flow forecast based on the predicted values of the parameters. Results of example show that the combination of the two kinds of methods can not only improve the accuracy of the prediction, but also fit the situation that there are singular points in the parameter sequences. The introduction of PGAGO GM (1,1) model makes the model have more extensive applicability and practical meaning. Key words: Short-term traffic flow; Multi-level recursive method; PGAGO GM (1, 1); Grey prediction
其他摘要：The prediction of short-term traffic flow has become one of the core researched content of ITS, and plays a key role in traffic management and control. Considering the concept of time varying parameters and the volatility of traffic flow data, multi-level recursive method based on PGAGO(Generalized Accumulated Generating Operation) GM (1,1) is adopted in this paper to improve the accuracy of the prediction and make the prediction model more tally with the actual situation. The forecast step is divided into two parts: the prediction of model parameters and traffic flow forecast based on the predicted values of the parameters. Results of example show that the combination of the two kinds of methods can not only improve the accuracy of the prediction, but also fit the situation that there are singular points in the parameter sequences. The introduction of PGAGO GM (1,1) model makes the model have more extensive applicability and practical meaning. Key words: Short-term traffic flow; Multi-level recursive method; PGAGO GM (1, 1); Grey prediction
