摘要
为准确预测路网整体的车辆运行状态,利用MFD在外界相似条件下具有良好再现性的重要性质,提出一种基于(包括时间轴在内的)三次元MFD和ARIMA模型的区域宏观交通状态的短时预测方法。该模型由表征历史数据特征的趋势项与表示预测当天宏观交通状况微小变动的随机项等2部分组成。其中,趋势项由三次元MFD的历史数据计算得出,随机项由ARIMA模型计算得出。以日本冲绳县那霸市中心商业区为例进行分析,结果表明,该模型可以较小的相对误差来实现对未来短时间内(30 min)的区域宏观交通状态预测。
A short-time forecast method for regional macro traffic status was proposed based on the three-dimensional MFDs(including time axis)and ARIMA model,using the reproducibility of MFDs under similar conditions to forecast the vehicles’operation in the road network,which consisted of trend term that was calculated by the historical data from three-dimensional MFDs,and random term that was calculated by ARIMA mode and represented the variation of the traffic accumulation and the traffic production on forecasting day.Taking the Naha-city(Japan)as an example,an empirical analysis was conducted,and the result showed that the proposed model can forecast the macro traffic status in 30-min with small relative error.
作者
王鹏飞
WANG Pengfei(College of Urban Construction,Hebei Normal University of Science&Technology,Qinhuangdao Hebei,066004;Key Laboratory of Urban Security and Disaster Engineering of Ministry of Education,Beijing University of Technology,China)
出处
《河北科技师范学院学报》
CAS
2021年第1期67-72,共6页
Journal of Hebei Normal University of Science & Technology
基金
河北省自然科学基金项目(项目编号:E2018407051)
河北省引进留学人员资助项目(项目编号:C20190333)
河北科技师范学院省属高校基本科研业务费项目(项目编号:2020JK020)。
