Study On The Methods Of Trafic Parameters Short-term And Multi-steps Prediction For Urban Road

Traffic congestion affects greatly the further development of urban and travel of people. ITS can solve the serious traffic problem. Traffic parameters prediction is an important research item in the field of Intelligent Transportation Systems. It can provide real-time, accurate, reliable traffic parameters prediction information about road traffic operation state for its core subsystems Advanced Traveler Information System and Advanced Transport Management Systems of the ITS, so that ITS can quickly and accurately find out road network operation state, then adopt according measures to dismiss congestion and make the benefit of the society and the economy biggest. However, the inadequate of the existing traffic parameters data particular the forecast data has become a bottleneck, restricting the development of the Intelligent Transportation Systems. So it is necessary to do further research on forecast traffic parameters technology, especially the prediction technology of short-term and multi-steps traffic parameters, which plays an important role for the development of the Intelligent Transportation Systems.This paper studies the methods of the short-term and multi-steps traffic parameters prediction for urban road, based on the subproject"access to technology of traffic control related condition"of the item"the study on key technologies of intelligent traffic control system", funded by National Hi-tech Research and Development Plan under grant 2006AA11Z228.This paper comprises of 6 chapters, and their contents are as follows:Chapter 1: Introduction. Introduce the project origin and explain what and why to be investigated in this paper. Point out the value of this paper both from theory and practice, and then summarize the research status both at home and abroad. At last, the main contents and structure of this paper are given.Chapter 2: Framework design of the Short-term and Multi-steps Traffic-parameters Prediction System. Design the system framework based on analysis of user requirement and function demand, and then analyze critical technologies of the function modules to identify the main research contents.Chapter 3: Study on the analysis method of traffic parameters'predictability. This part analyzed the traffic flow's chaotic characteristics under different time scales, used state space Reconstruction Technique to design an analysis method of traffic parameters'predictability, which provided technical support for the prediction precision.Chapter 4: Study on the methods of traffic parameters short-term and multi-steps prediction for Urban Road. The methods of short-term and multi-steps traffic parameters prediction were proposed based on history date and the technology of Adaptive Weight Exponential Smoothing, RBF neural network and Kalman filter. Then the critical problem—similarity searching technology of time series were discussed. At last a new prediction method based on data fusion, named Multi-Model Fusion Algorithm (MMFA) was designed.Chapter 5: The case study was performed with simulated data. The results showed that the proposed short-term and multi-steps prediction methods have nice practicability and different forecasting accuracy.Chapter 7: Concludes the whole paper, summaries the findings and achievements, and brings forward the issues for further research.