Title :
Short-term traffic flow time series forecasting based on grey interval forecasts method
Author :
Li, Xingyi ; Xinghua, Zhang ; Shi, Huaji
Author_Institution :
Sch. of Comput. Sci. & Telecommun. Eng., Jiangsu Univ., Zhenjiang, China
Abstract :
Based on the randomness and uncertainty of short-term traffic volume time series, a grey interval forecasts method combined with threshold value analysis and interpolation analysis is put forward, aim to solve the interval grey model for coping with limited and secondary interval data. According to the stepwise ratio, lots of discussions have been made on threshold value analysis. And then, the upper envelope and the lower envelope are surveyed and marked off under distribution law of traffic data. After that, the grouped-data are used for interpolation analysis. In the end, GM(1,1) model is established to simulate the sequence, through which the range of predicted values are obtained. The New Information Principle in Grey System Theory ensures that this interval forecast method has a good anti-interference ability and fault tolerance, experiments show the interval forecast method has high accuracy.
Keywords :
fault tolerance; forecasting theory; grey systems; interpolation; road traffic; time series; transportation; GM(1,1) model; antiinterference ability; fault tolerance; grey interval forecast method; grey system theory; interpolation analysis; short-term traffic flow time series forecasting; threshold value analysis; traffic data; Analytical models; Predictive models; GM(1,1)model Introduction; Interval forecasts; interpolation analysis; short-term traffic volume forecasts; stepwise ratio; threshold value analysis;
Conference_Titel :
Educational and Information Technology (ICEIT), 2010 International Conference on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-8033-3
Electronic_ISBN :
978-1-4244-8035-7
DOI :
10.1109/ICEIT.2010.5607689
