摘要
实时路段行程时间预测是动态交通分配中路径选择的关键技术之一.采用微观交通仿真手段和指数平滑方法估计路段行程时间,在路段行程时间估计模型中考虑了交叉口排队延误、信号控制延误和交叉口内转向行程时间,提出了基于灰色等维新息GM(1,1)模型的路段行程时间预测方法,根据路段行程时间的历史数据和实时采集数据,滚动预测未来的路段行程时间,通过实例应用证明了模型有很好的预测精度.
Real-time link travel time prediction is one of the key technologies for the route choice of dynamic traffic assignment. Link travel time was estimated using microscopic traffic simulaition and exponential smoothing. The estimation model of link travel time took into account intersection queue delay, signal control delay and intersection turning delay. The prediction method of link travel time based on gray equal-dimension and new-info model was proposed. According to history data and real-time acquisition data of link travel time, the model predicted future link travel time by roll method. Finally, the prediction model was proved to have very good precision by example.
出处
《武汉理工大学学报（交通科学与工程版）》
2009年第3期411-413,417,共4页
Journal of Wuhan University of Technology（Transportation Science & Engineering）
基金
国家863计划项目(批准号:2007AA11Z203)
国家自然科学基金项目(批准号:50808123)
中国博士后基金项目(批准号:20070420657)资助
关键词
微观交通仿真
路段行程时间
灰色等维新息模型
指数平滑
microscopic traffic simulation
link travel time
gray equal-dimension and new-info model
exponential smoothing
