摘要
论述了短时交通流预测模型的分类、特点和适用条件。通过历史交通流量记录运用最优抽样间隔数据分析发现,在城市道路网络中,路口自身和近邻路口的交通流数据之间存在紧密的时空关系。利用时空自回归移动平均模型来建立路口间交通流的时空关联关系,用于区域交通流的短时预测和时空分析,并详细介绍了该模型的数学描述和建模过程。采用长安街及其沿线路口的区域交通流量作为试验数据,验证了该模型在交通流的短时预测和时空分析中的可行性。该模型在考虑预测值所在位置时间序列的同时,也考虑到了空间上相邻位置的时间序列,大大提高了短时交通流预测的准确性。
Classification, features and applicability of short term traffic flow forecast models are reviewed at first. Based on data analysis of historical traffic volume datasets using the optimized sampling interval method, close spatial and temporal associations exist between traffic flow of the intersection and its neighbors in the urban traffic network. Space-time autoregressive moving average model is utilized to develop this relationship in space and time between traffic flow of each intersection, and to forecast and explore traffic flow in space and time. Mathematical description and development procedure of the model are also introduced and described specifically. Traffic volume datasets of the intersections located on the Chang' an Steer and its related roads are used as the sample datasets to verify model' s applicability in short term forecast and spatial and temporal analysis. Not only traffic time series datasets of some intersection but also those of its spatial neighbors are used to estimate the short term traffic flow in the model, and the results show that the prediction accuracy is improved greatly.
出处
《公路交通科技》
CAS
CSCD
北大核心
2007年第6期92-96,共5页
Journal of Highway and Transportation Research and Development
基金
国家自然科学基金资助项目(40471111)
北京市自然科学基金资助项目(8033015)
关键词
智能运输系统
交通流时空预测
时空自回归移动平均模型
时空关联关系
Intelligent Transport Systems
traffic volume forecasting in space and time
space-time autoregressive moving average model
spatial and temporal association