基于时间序列分析的上海地铁16号线客流预测—以临港大道站为例.pdf

Operations Research and Fuzziology 运筹与模糊学, 2016, 6(1), 15-26 Published Online February 2016 in Hans. /journal/orf /10.12677/orf.2016.61003 Prediction of Shanghai Metro Line 16 Passenger Flow Based on Time Series Analysis —with Lingang Avenue Station as a Study Case 1 2 1 1 Yanli Chen , Yuwu Sha , Xiaolin Zhu , Xiaohong Zhang 1 College of Arts and Sciences, Shanghai Maritime University, Shanghai 2 Ministry of Operational Scheduling, Shanghai Maglev Transportation Development Co. Ltd., Shanghai th th rd Received: Jan. 27 , 2016; accepted: Feb. 17 , 2016; published: Feb. 23 , 2016 Copyright © 2016 by authors and Hans Publishers Inc. This work is licensed under the Creative Commons Attribution International License (CC BY). /licenses/by/4.0/ Abstract Problems emerge along with the continuous development of urban rail transit, and how to predict the passenger flow to improve the efficiency of the rail transit operation by the scientific method has caused widely public concern. Time series analysis is the mainstream of forecasting method. And ARIMA model acts on all kinds of sequences, so it is the most common time series prediction method by far. This study proposes Autoregressive Integrated Moving Average Model (ARIMA model) to predict the passenger flow data of the line 16 Lingang Avenue Station based on the historical datum through time series analysis in order to improve the operational efficiency of the urban rail transit and effective cohesion with buses in Lingang area. We utilize the autocorrelation and partial auto- correlation function to preliminarily judge and identify the par