计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (19): 343-353.DOI: 10.3778/j.issn.1002-8331.2306-0338

• 工程与应用 • 上一篇    下一篇

考虑站点分类的城市轨道短时客流预测方法

王泰州,  徐金华,  陈姜会,  李岩,  任璐   

  1. 1. 长安大学 运输工程学院, 西安  710064
    2. 长安大学 学术期刊管理中心, 西安  710064
  • 出版日期:2024-10-01 发布日期:2024-09-30

Short-Term Passenger Flow Prediction Method for Urban Rail Transit Considering Station Classification

WANG Taizhou, XU Jinhua, CHEN Jianghui, LI Yan, REN Lu   

  1. 1. College of Transportation Engineering, Chang’an University, Xi’an 710064, China
    2. Chang’an University Journal Center, Xi’an 710064, China
  • Online:2024-10-01 Published:2024-09-30

摘要: 精确、可靠的短时客流预测可为城市轨道交通运营提供保障。考虑不同站点的客流时序特征差异,在对站点分类的基础上,建立了一种城市轨道站点客流的深度学习预测方法。以动态时间规整及K-means算法对站点进行分类,分析各类站点的客流时序特征;采用自适应噪声完全集成经验模式分解算法对各类站点客流数据进行分解,以减少数据噪声的影响;提出一种融合长短期记忆网络和Transformer模型的深度学习预测方法,从而预测不同类型站点客流。应用西安市轨道交通客流数据验证该方法,结果表明:根据工作日及非工作日的客流数据时序特征可将站点分为职住均衡型、商务办公型、休闲娱乐型和密集居住型4类,所提出的方法在不同类型站点的客流预测结果相比于其他3种单一模型和3种组合模型,平均绝对误差降低16.36%~51.02%、均方根误差降低10.35%~50.76%,平均绝对百分比误差降低14.71%~48.62%,基于15 min、30 min、45 min及60 min不同时间间隔统计的站点客流数据的预测结果相比于其他6种模型,3种指标分别降低了12.63%~51.02%、8.08%~49.12%和6.83%~47.26%。

关键词: 城市轨道交通, 短时预测, 站点分类, 自适应噪声完全集成经验模式分解算法, 长短期记忆网络, Transformer

Abstract: Accurate and reliable short-term forecasting of passenger flows can ensure the operation of urban rail transport. Considering the differences in the timing characteristics of passenger flows at different stations, a deep learning method for predicting passenger flows at urban stations is developed based on station classification. Firstly, stations are classified by dynamic time warping and the K-means algorithm, and the timing characteristics of the passenger flow of various stations are analyzed. Secondly, the complete ensemble empirical mode decomposition with adaptive noise is used to decompose passenger flow data of various stations to reduce the effects of data noise. Finally, a deep learning prediction method integrating long short-term memory and Transformer model is proposed to predict the passenger flow of different types of stations. The method is verified by using the passenger flow data of Xi’an Metro. The results show that the stations can be classified into four types according to the timing characteristics of passenger flow data on working days and non-working days: occupation-residential balance type, business office type, leisure and entertainment type, and dense residential type. Compared with the other three single models and three combined models, mean absolute error of passenger flow prediction results of the proposed method in different types of stations is reduced by 16.36%~51.02%, root mean square error is reduced by 10.35%~50.76%, and mean absolute percentage error is reduced by 14.71%~48.62%. Compared with the other six models, the prediction results of the station passenger flow data based on the statistics of different time intervals of 15 min, 30 min, 45 min and 60 min, the three indicators are respectively reduced by 12.63%~51.02%, 8.08%~49.12% and 6.83%~47.26%.

Key words: urban rail transit, short-term prediction, station classification, complete ensemble empirical mode decomposition with adaptive noise, long short-term memory network, Transformer