交通运输系统工程与信息

交通运输系统工程与信息 ›› 2015, Vol. 15 ›› Issue (6): 205-211.

• 案例分析 • 上一篇    下一篇

基于SARIMA 模型的北京地铁进站客流量预测

王莹a，韩宝明*a，张琦b，李得伟b   

  1. 北京交通大学a. 轨道交通控制与安全国家重点实验室；b. 交通运输学院，北京100044
  • 收稿日期:2015-04-28 修回日期:2015-06-20 出版日期:2015-12-25 发布日期:2015-12-25
  • 作者简介:王莹（1991-），女，山西太原人，博士生.
  • 基金资助:

    中央高校基本科研业务费专项资金资助（2015JBM046）；北京交通大学基本科研业务费资助项目（2014JBZ008, 2014JBM058,2012RC028）；高等学校博士学科点专项科研基金资助课题（20120009120019）；北京高等学校“青年英才计划” （YETP0555）

Forecasting of Entering Passenger Flow Volume in Beijing Subway Based on SARIMA Model

WANG Yinga, HAN Bao-minga, Zhang Qib, Li De-weib   

  1. a. State Key Laboratory of Rail Traffic Control and Safety; b. School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China
  • Received:2015-04-28 Revised:2015-06-20 Online:2015-12-25 Published:2015-12-25

PDF

被引次数

9

摘要：

通过对北京地铁2013 年5 月~7 月的进站客流量数据进行详细分析，总结北京 地铁进站客流量以周为周期的波动规律，选用季节时间序列（SARIMA）模型对北京地铁 进站客流量进行时间序列建模.利用符合要求的模型对北京地铁进站客流量进行预测，预 测结果能够较准确地描述北京地铁进站客流量的变化趋势，平均误差为0.3%.说明此模型 适用于地铁进站客流量的短时预测，基于预测结果进一步分析北京地铁进站客流量的特 点，为进一步优化进站设施布置、组织进站流线、高效安全的地铁运营组织提供参考建议.

关键词: 城市交通, 客流量预测, SARIMA模型, 进站客流量, 时间序列

Abstract:

Based on the inbound traffic data of Beijing subway from May 2013 to July 2013, this paper analyzes and summarizes the fluctuation of Beijing subway inbound traffic data from weekly cycle. In the process of modeling, the seasonal time series (SARIMA) model is used. Using the model to predict the traffic flow in Beijing subway, the forecast results can accurately describe the change trend of the traffic flow in Beijing subway station, the average error is 0.3%. The result shows that the model is suitable for the prediction of the traffic flow in the Beijing subway. Based on the forecast model results, further analysis of the characteristics of the entering passenger flow volume is analyzed. And the reference suggestions are provided for the further optimization of the layout of the station facilities, the flow line of the organization and the efficient and safe operation of the subway.

Key words: urban traffic, passenger flow volume forecasting, SARIMA model, entering passenger flow volume, time series

中图分类号: