Infrastructure Modeling and Optimization to Solve Real-time Railway Traffic Management Problems

Lindenmaier, László; Lövétei, István Ferenc; Lukács, Gábor; Aradi, Szilárd

doi:10.3311/pptr.18582

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The alternate graph method is suitable to solve the problem as well [7]. Another option is to use the mixed linear integer programming method, as the authors suggest in [8]. OpenTrack environment can provide a base for the implementation [9].…”

Section: B Related Workmentioning

confidence: 99%

Multi-Agent Reinforcement Learning for railway rescheduling

Kővári,

Balogh,

Aradi

2023

2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)

Self Cite

View full text Add to dashboard Cite

Malfunctions, congestions, and accidents occur in every railway system from time to time, which influences the railway traffic on a given section of the system. The disturbance may cause inconvenience for several passengers and disruption in rail freight. Both the schedule and route of the affected trains must be modified to avoid further congestion and minimalize delays. The rigidity of the railway system (e.g., single tracks, vast distances without a service station, no viable alternative in case of malfunction) poses restrictions, unlike other transportation systems. Replanning schedules and train routes (called the railway rescheduling problem) is complex and demanding, even for human operators, as one must consider numerous factors. Thus, finding a satisfying solution poses a significant challenge. This paper presents a MARL-base (Multi-Agent Reinforcement Learning) solution that shows great potential for tackling this problem, even in the case of multiple connected stations.

show abstract

Section: B Related Workmentioning

confidence: 99%

Multi-Agent Reinforcement Learning for railway rescheduling

Kővári,

Balogh,

Aradi

2023

2023 IEEE 17th International Symposium on Applied Computational Intelligence and Informatics (SACI)

Self Cite

View full text Add to dashboard Cite

show abstract

RETRACTED ARTICLE: Sustainable regional rail system pricing using a machine learning-based optimization approach

Gokasar,

Karakurt,

Kuvvetli

et al. 2023

Ann Oper Res

View full text Add to dashboard Cite

Regional transport pricing is indeed very vital in urban settings where the transportation network is spread out across large areas and can influence travel behavior and the sustainability of cities. Therefore, in addition to existing pricing systems, such as flat fare, distance-based fare, and zonal pricing, this study proposes a sustainable approach to regional rail system pricing using rent prices and a transportation affordability index. The proposed model aims to reduce commuters' overall travel distance in order to reduce air pollution and maintenance costs for public transportation vehicles. Rent-based pricing encourages people to rent houses in regions that shorten their travel distances and fill a gap in the literature on regional rail system pricing by dealing with the decentralization of the cities. A two-step clustering and non-linear optimization modeling approach are proposed based on face-to-face surveys with regional rail system passengers. For various clusters of stations, rent per income rates and rental-based ticket prices were obtained. Furthermore, a sensitivity analysis is conducted to evaluate different conditions of the affordability index and rent prices in the studied regions. Compared to the current pricing system, ticket revenues increased by 3.88% and 1.68% in rent-based pricing.

show abstract

Runtime Performance Analysis of a MILP-Based Real-Time Railway Traffic Management Algorithm

Aradi,

Lindenmaier,

Lövátei

2023

2023 IEEE 21st Jubilee International Symposium on Intelligent Systems and Informatics (SISY)

View full text Add to dashboard Cite

The real-time railway traffic management problem occurs when the trains get off schedule due to different traffic perturbations. In this case, they must be rerouted, reordered, and rescheduled to resolve the possible conflicts. Nowadays, this problem is usually handled by human dispatchers. There are lots of algorithms aiming to support human dispatchers in making an optimal decision that minimizes delays. However, due to the real-time nature of the problem, the response time of these algorithms is crucial. In this paper, the runtime performance of a state-of-the-art mixed-integer linear programming model is analyzed in different solvers. The analysis is performed via Monte Carlo simulation, generating various realistic scenarios in an infrastructure model of a Hungarian railway control area.

show abstract

Infrastructure Modeling and Optimization to Solve Real-time Railway Traffic Management Problems

Cited by 4 publications

References 6 publications

Multi-Agent Reinforcement Learning for railway rescheduling

Multi-Agent Reinforcement Learning for railway rescheduling

RETRACTED ARTICLE: Sustainable regional rail system pricing using a machine learning-based optimization approach

Runtime Performance Analysis of a MILP-Based Real-Time Railway Traffic Management Algorithm

Contact Info

Product

Resources

About