Short-term Forecasting Of Traffic Flow With Chaos Theory On Urban Expressway

Real-time and accuratic short-term traffic flow forecasting has become a critical problem in Intelligent Transport Systems (ITS). In China's megapolis , especially Beijing, about 400 real-time traffic flow sensors at the section was located the urban expressway network. The control center get the data of per-two minutes. It is important significance and valuable to use this mass data of the traffic sensors to predict accurately the future traffic flow state of the urban expressway, for easing urban road traffic jams, the effective use of road resources, and reducing travel time. However, the participation of the drivers bring the random disturbance. This uncertainty of traffic state bring greater difficulties to predict accurately.To solve the problem above, this paper summarizes the research of the short-term traffic flow forecasting's theory and methods at home and abroad, and lucubrate the chaos theory. Firstly, this paper analyzes the issues related to the chaos theory. Secondly, it builts the traffic forecasting model of urban expressway with chaos theory. Thirdly, the model is applied to forecast traffic flow in an urban expressway of a single section and multi-sections. Lastly, it analyzes the predicted results, summarize research results and propose future research suggestions. The result shows that chaos theory has good performance in describing a nonlinear and random traffic phenomena.