交通运输系统工程与信息 ›› 2017, Vol. 17 ›› Issue (1): 74-81.

• 智能交通系统与信息技术 • 上一篇    下一篇

考虑多因素的城市道路交通拥堵指数预测研究

韦清波* 1,何兆成2, 4,郑喜双3,陈昶佳1,杨敬锋1   

  1. 1. 广州市公共交通数据管理中心,广州510620;2. 中山大学智能交通研究中心,广州510275; 3. 广州市交通信息指挥中心,广州510620;4. 广东省智能交通系统重点实验室,广州510006
  • 收稿日期:2016-06-02 修回日期:2016-08-03 出版日期:2017-02-25 发布日期:2017-02-27
  • 作者简介:韦清波(1984-),男,广东高州人,工程师,硕士.
  • 基金资助:

    广东省省级科技计划项目/ Provincial Science and Technology Program of Guangdong Province(2014B010118002);广 东省交通运输厅科技项目/Science and Technology Program of Guangdong Provincial Department of Transportation (科技- 2014-02-046).

Prediction of Urban Traffic Performance Index Considering Multiple Factors

WEI Qing-bo 1,HE Zhao-cheng2, 4,ZHENG Xi-shuang3,CHEN Chang-jia1 ,YANG Jing-feng1   

  1. 1. Guangzhou Public Transport Data Management Center, Guangzhou 510620, China; 2. ITS Research Institute, Sun Yat-sen University, Guangzhou 510275, China; 3. Guangzhou Transport Information & Control Center,Guangzhou 510620, China; 4. Guangdong Provincial Key Laboratory of Intelligent Transportation System, Guangzhou 510006, China
  • Received:2016-06-02 Revised:2016-08-03 Online:2017-02-25 Published:2017-02-27

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.

关键词: 城市交通, 中短期预测, K 近邻, 交通拥堵指数, 多因素

Abstract:

Based on studying the change rules of macroscopic urban traffic, and comprehensive consideration the factors on the impact of traffic, such as: weather, holidays, major activities other factors, this paper establishes a K-Nearest Neighbor traffic performance index prediction model for the next 3 hours and 24 hours (every 5 minutes). Taking the effect of all the related factors into account, the model designs the state vectors, distance calculation and the prediction calculation method, calibrates parameters of the model with historical data, and then the traffic performance index of mid-term and short-term can be predicted. The test result with the traffic performance index of Guangzhou proves the proposed model has ideal prediction on both normal and special days with strong practicability and maneuverability

Key words: urban traffic, short and medium term prediction, KNN, traffic performance index, multi-factors

中图分类号: