A Stochastic Process Approach for Modeling Arrival Delay in Train Operations
Compared with air and road transport, railway transport nowadays plays an essential role in catering for continuously increasing travel demand in Sweden given its high capacity and convenience. However, as the demand approaches the maximum capacity, issues like delay propagations undermine the punctuality and reliability of railway systems. Nevertheless, punctuality in train operation is usually considered as the major indicator when passengers evaluate the service performance of railway transport. This study, therefore, attempts to quantify the relationship between the arrival delays of passenger trains and their influential factors in operation and weather condition. A stochastic modeling approach based on Wiener process is introduced to analyze the train operation. The model parameters are estimated by the maximum likelihood estimation approach. A case study is carried out using data of two rail paths connecting two main railway stations, Stockholm Center and Örebro Center over a one-year period in 2009. Three data sources, consisting of train movement information, rail failure data, and weather data, are applied in this study. Models are specified and then estimated using part of the available data. Finally, several goodness-of-fit measures are evaluated to validate and compare different model specifications using an independent dataset. As a result, it is found that the predicted arrival delays have a similar tendency to the actual arrival delays. The estimation results of the model taking weather condition into account fit the actual arrival delays more precisely, largely supporting the hypotheses proposed.
-
Supplemental Notes:
- This paper was sponsored by TRB committee AP070 Standing Committee on Commuter Rail Transportation.
-
Corporate Authors:
500 Fifth Street, NW
Washington, DC United States 20001 -
Authors:
- Qin, Yuanqi
- Ma, Xiaoliang
- Jiang, Sida
-
Conference:
- Transportation Research Board 96th Annual Meeting
- Location: Washington DC, United States
- Date: 2017-1-8 to 2017-1-12
- Date: 2017
Language
- English
Media Info
- Media Type: Digital/other
- Features: Figures; Maps; References; Tables;
- Pagination: 19p
- Monograph Title: TRB 96th Annual Meeting Compendium of Papers
Subject/Index Terms
- TRT Terms: Arrivals and departures; Delays; On time performance; Stochastic processes; Train operations; Weather conditions
- Geographic Terms: Stockholm (Sweden)
- Subject Areas: Operations and Traffic Management; Planning and Forecasting; Railroads;
Filing Info
- Accession Number: 01625968
- Record Type: Publication
- Report/Paper Numbers: 17-02466
- Files: TRIS, TRB, ATRI
- Created Date: Feb 15 2017 5:02PM