北京交通大学学报2018，Vol.42Issue(1)：87-93,7.DOI:10.11860/j.issn.1673-0291.2018.01.013
基于AFC数据的大型活动期间城市轨道交通客流预测
Urban rail transit passenger flow forecasting for large special event based on AFC data
摘要
Abstract
Accurately forecasting the urban rail transit (URT) passenger flow during the large special event is the foundation of preparing transport organization plan for the URT management and operation department,and also the key to guarantee the passenger transportation during the event.Based on the analyses of the URT history passenger flow during the event,two forecasting models for the two passenger flow components (event related and background passenger flow) are respectively proposed to realize the passenger flow forecasting.The characteristics of passenger flow is analyzed based on the data collected by Automated Fare Collection(AFC) system,and is decomposed into two components.A wavelet decomposed and reconstructed based GM-ARIMA forecasting model is proposed to forecast event-related passnger flow,and ARIMA model and Detroit method is used to forecast the background passenger flow.The proposed models are testified with the AFC data collected from Guangzhou Metro system from 2011 to 2014's China Canton Fair.The results show that the proposed models could capture the characteristics of the passenger flow during the event,which has good forecasting performances.关键词
城市轨道交通/大型活动/客流预测/背景客流/活动客流/AFC数据Key words
urban rail transit/large special event/passenger flow forecasting/background passenger flow/event-related passenger flow/AFC data分类
交通工程引用本文复制引用
王兴川,姚恩建,刘莎莎..基于AFC数据的大型活动期间城市轨道交通客流预测[J].北京交通大学学报,2018,42(1):87-93,7.基金项目
北京市自然科学基金(8171003) Beijing Municipal Natural Science Foundation(8171003) （8171003）
