Real-time Dynamic Transportation Guidance Method With Self-update Mechanism And Prediction Ability

In recent years,with the rapid development of Chinese economy,the number of motor vehicles has always maintained a rapid growth rate,the substantial increase in the number of motor vehicles has led to urban traffic congestion become prominent.How to solve the problem of traffic congestion quickly and effectively on the base of existed road infrastructure has become an urgent problem in the field of intelligent transportation,however,the research of dynamic route guidance system is the focus of intelligent transportation.The key to the dynamic route guidance system is how to make the vehicles are reasonably assigned to different roads under the make full use of the existed road resources,so that the whole road network to keep the optimal condition.This paper presented a new real-time vehicle guidance method,combined with short-time traffic condition prediction,dynamic traffic assignment,intelligent release algorithm and two types of real-time monitoring and self-adjustment mode,forming a intelligent guidance method that can dynamic self-validation and update.Compared with the traditional traffic guidance method,this paper presented the method is more adapt to the real situation,such as dynamic change of traffic condition,the driver's uncertain attitude to released information.This method can better achieve the effect of balancing the traffic pressure through self-validation and self-update mechanism.In view of short-term traffic prediction of intelligent guidance method,and based on BP Neural Network and improved Kalman Filter,this paper presented a combined prediction model.And the real data of Jingshi road in Jinan are analyzed,in the four scenes,compared the prediction effect of BP Neural Network model,improved Kalman Filter model and combined prediction model with the aspects of accuracy and reliability,the result demonstrate the effectiveness of combined prediction model.In view of dynamic traffic assignment of intelligent guidance method,this paper based on two of the dynamic traffic assignment model,they are the system optimal assignment model and the user optimal assignment model.Considered the benefit relation between the administrators and the travelers and the conflict between them is analyzed based on Game Theory.In order to solve the traffic assignment problem in the road network,this paper presented a Game Theory assignment method that optimized by Genetic Algorithm.Taking the Qianfo Mount campus network of Shandong University as the case study,to demonstrate the effectiveness of the Game Theory assignment method that optimized by Genetic Algorithm.In view of intelligent dynamic release and real-time validation of intelligent guidance method,and based on the analysis of influencing factors of drivers' route choice behavior and guidance information release strategy,this paper presented a guidance information release and validation mechanism.By analyzing the difference between the actual guidance effect and the expected guidance effect after the guidance information release to determine whether need to adjust release strategy or traffic assignment again,forming a complete guidance loop that included time prediction,traffic assignment,guidance information release,and guidance effect validation.