考虑多因素的城市道路交通拥堵指数预测研究
发布时间：2018-10-24 14:08
【摘要】：在分析城市道路交通拥堵指数总体变化规律的基础上,综合考虑天气、节假日、重大活动等因素对交通的影响,以未来3 h、第2天24 h每5 min的交通拥堵指数明细为预测目标函数,建立基于K近邻的城市道路交通拥堵指数预测模型,确定了模型的状态向量、距离计算方法、预测值计算方法等,并根据实际采集数据对模型各参数进行标定,实现了对广州市宏观交通拥堵指数的短期、中期预测.最后,以2016年1~2月的数据为例,对模型进行测试验证.结果表明,预测模型对于普通日、特殊日的预测效果理想,且具有较强的可操作性,基本达到工程应用效果.
[Abstract]:On the basis of analyzing the general changing law of urban road traffic congestion index, considering the influence of weather, holidays, major events and other factors on traffic, Taking the traffic congestion index of 24 hours per 5 min in the next 3 hours and the second day as the forecasting objective function, a forecast model of traffic congestion index of urban road based on K nearest neighbor is established, and the state vector and distance calculation method of the model are determined. Based on the actual data collected, the parameters of the model are calibrated, and the short-term and medium-term prediction of the macroscopic traffic congestion index of Guangzhou is realized. Finally, taking the data from January to February 2016 as an example, the model is tested and verified. The results show that the prediction model is ideal for ordinary days and special days, and has strong maneuverability, and basically achieves the engineering application effect.
【作者单位】： 广州市公共交通数据管理中心;中山大学智能交通研究中心;广东省智能交通系统重点实验室;广州市交通信息指挥中心;
【基金】：广东省省级科技计划项目(2014B010118002) 广东省交通运输厅科技项目(科技-2014-02-046)~~
【分类号】：U491.265
，
本文编号：2291627
[Abstract]:On the basis of analyzing the general changing law of urban road traffic congestion index, considering the influence of weather, holidays, major events and other factors on traffic, Taking the traffic congestion index of 24 hours per 5 min in the next 3 hours and the second day as the forecasting objective function, a forecast model of traffic congestion index of urban road based on K nearest neighbor is established, and the state vector and distance calculation method of the model are determined. Based on the actual data collected, the parameters of the model are calibrated, and the short-term and medium-term prediction of the macroscopic traffic congestion index of Guangzhou is realized. Finally, taking the data from January to February 2016 as an example, the model is tested and verified. The results show that the prediction model is ideal for ordinary days and special days, and has strong maneuverability, and basically achieves the engineering application effect.
【作者单位】： 广州市公共交通数据管理中心;中山大学智能交通研究中心;广东省智能交通系统重点实验室;广州市交通信息指挥中心;
【基金】：广东省省级科技计划项目(2014B010118002) 广东省交通运输厅科技项目(科技-2014-02-046)~~
【分类号】：U491.265
，
本文编号：2291627
本文链接：https://www.wllwen.com/kejilunwen/daoluqiaoliang/2291627.html
