Abstract
Metro trains stop operation during midnight for the maintenance of vehicles and tracks in most cities, where passengers heavily rely on the metro for their daily life. Thus, passengers may miss the last trains when they travel by metro at late night. However, the last trains are especially important because they are the last chances for many passengers to travel by metro. If passengers miss the last trains, they have to choose buses, taxies, or other transport modes to complete their trips. Consequently, it is necessary to optimize the schedule of the last train coordination to meet the demand of passengers at transfer stations during midnight. The passenger demand for last trains is a vital input to deal with the coordination of last train transfers. This paper focuses on forecasting the potential passenger demand of last trains from public transport data including taxi (FCD data) and bus (GPS/smart data) systems. A solution for taxi and bus data is developed to calculate the potential passenger demand for all the transfer directions of the target stations. Then, a model for the coordination of last train transfers based on the potential passenger demand is proposed. The genetic algorithm is applied to solve the model. The effectiveness of the proposed method is evaluated using the Shenzhen metro network with several data on a typical Friday. The research is to provide theoretical guidance and technical reference for the metro operation when to compile the last train schedule. It is supposed to improve the modern operation management level of metro systems.
Highlights
Metro system is a kind of transportation system with the advantages of large capacity, rapidness, punctuality and comfort, which can effectively solve many problems such as high population density, large traffic jam, and road congestion in large cities
The station dwelling time and the section running time are regarded as fixed parameters, the last train coordination can be achieved by the adjustment of the departure time of last trains from the original station in different metro lines
This paper focuses on the coordination of last train transfers using potential passenger demand from public transport modes including taxi and bus
Summary
Metro system is a kind of transportation system with the advantages of large capacity, rapidness, punctuality and comfort, which can effectively solve many problems such as high population density, large traffic jam, and road congestion in large cities. It is worth noting that in recent years that new technologies and equipment in urban traffic system have been put into use continuously, and abundant data resources have been accumulated in the process of operation and management, such as GPS data (Global Positioning System Data), smart card (Integrated Circuit Card) swipe data recorded by bus transit system, FCD data (Floating Car Data, Floating Vehicle Data) recorded by taxi transit system These accumulating data have been reaching a huge amount over time as a big data, which can be used to calculate the potential passenger demand for last trains. In order to study the coordination of last train transfers in metro system, this paper mainly selects diversified public transport data resources to analyze and predict the potential passenger demand for last train transfers, including AFC data and train operation data of metro system, GPS data and smart card swipe data of bus system, FCD data of taxi system.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
