Short-term traffic flow prediction based on GM(1,1,Exp) model

摘要

In this paper, we use the gray model through the consolidation of original data to find the changing laws of the system, to generate a strong regularity of the data series, thus well predict the changing trend of the future. Meanwhile, considered the defect that the grey action of traditional GM(1,1) model is constant, we introduce a sine function relation and make the grey action into a dynamic variable which contains time function. Thus, the traditional GM(1,1) model is optimized. Finally, the result shows that the optimized GM(1,1) model can simulate better, and has a higher accuracy.