Research On Short-time Traffic Flow Forecasting For Urban Traffic Control

Intelligent transportation system(ITS) is considered as one of the effective methods to relieve the urban traffic problems such as traffic congestion,accidents and air pollution caused by motor vehicle exhausts.By gathering and analysising the real-time data of urban road network,short-time traffic flow forcasting could estimate the state of traffic flow for a few minutes in future and provide support to intelligent transportation control,so it is one of the important premise for ITS.Research on short-time traffic flow forecasting for urban traffic control is discussed in this dissertation,based on the requirement analysising of urban traffic control system,the relativity between several traffic flows in urban road network is discussed.According to the relativity,urban road network is devided to smaller area,and the research of short-time traffic flow forecasting is studied in the smaller areas.At first,this dissertation explains the study background and meaning of research on short-time traffic flow forecasting for urban traffic control,and introduces the general situation and short-time traffic flow forecasting methods of the main urban traffic control system.And introduces the basic conceptions and theories of urban traffic control and traffic flow,the characteristic of traffic flow is talked about also.Then,the multidimensional scaling in multivariate statistical analysis is used for analysising the relativity between traffic flows in urban road network,so as to determine the area of short-time traffic flow forecasting.And based on an early theory of short-term traffic flow forecasting,a new kind of short-time traffic flow forecasting model is designed,which is added with the study of traffic jam detection and effect evaluation.At the end,simulation is proceeded on a open-source simulation platform.The result shows that this forecasting model could basicly meet the real-time and accurate requirement of urban traffic control.