Urban rail transit passenger flow forecasting for large special event based on AFC data
WANG Xingchuan
YAO Enjian
LIU Shasha
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.
Keywords：urban rail transitlarge special eventpassenger flow forecastingbackground passenger flowevent-related passenger flowAFC data
Publication Date：2018-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：7( 87-93 )