A Novel Hybrid Model for Short-Term High-Speed Railway Passenger Demand Forecasting

Shuo Zhao,Xiwei Mi

doi:10.1109/access.2019.2957612

Shuo Zhao, Xiwei Mi

Open Access

https://doi.org/10.1109/access.2019.2957612

Copy DOI

Abstract

As a critical input, high-speed railway (HSR) passenger demand is a significant guide for railway planning and operation. Accordingly, the necessity of accurately forecasting short-term demand has become a pressing problem; it has increasingly attracted attention as a research interest. In this paper, a novel hybrid model, specifically, the SSA–WPDCNN–SVR model, is proposed for short-term HSR passenger demand forecasting that explicitly considers the relevance of neighbour time data. The model consists of three procedures: (i) the decomposition of the original time series into the principal component (PC) and several detailed components (DCs) by the singular spectrum analysis (SSA) method, which is adopted as the signal processing procedure; (ii) the forecasting of PC by means of the designed convolutional neural network with the wavelet packet decomposition (WPDCNN) through the transformation of the one-dimensional time series into weekly cross-correlation matrices (i.e., image-like two-dimensional data); (iii) the forecasting of DCs by the support vector regression (SVR) method. The case studies of three typical origin–destination pairs in an HSR line are considered to demonstrate the validity and correctness of the proposed model, which not only extracts the fluctuation characteristics of passenger flows, but also outperforms several other existing models with its higher short-term HSR demand forecasting accuracy.

Highlights

The continuous socio-economic development and increasing travel demand have led to high-speed railway (HSR) advancement
We propose a novel hybrid model for forecasting the short-term HSR passenger demand that explicitly considers the relevance among neighbour time data
It can be shown that the forecasted results perform well in the three O–D pairs, except one or two data points, which results from the statistical error of the original data

Summary

Introduction

The continuous socio-economic development and increasing travel demand have led to high-speed railway (HSR) advancement. The largest HSR network in the world has been constructed over the past decade in China; it has relieved the travel pressure caused by the huge number of commuters between major cities. To further satisfy various passenger travel requirements, effective railway planning procedures, including network design, line planning, and seat allocation, should be demand-sensitive to improve the service quality. As a significant input into railway planning and operation, accurate short-term passenger demand forecasts are urgently required to aid in adjusting existing operational plans to improve the service level, and to save operational costs. Short-term passenger demand forecasting has increasingly attracted attention as a research interest.

Methods

Results

Conclusion