@article{MTMT:35638375,
	title = {Efficient real-time rail traffic optimization: Decomposition of rerouting, reordering, and rescheduling problems},
	url = {https://m2.mtmt.hu/api/publication/35638375},
	author = {Lövétei, István Ferenc and Lindenmaier, László and Aradi, Szilárd},
	doi = {10.1016/j.jrtpm.2024.100496},
	journal-iso = {J RAIL TRANSP PLAN MANAG},
	journal = {JOURNAL OF RAIL TRANSPORT PLANNING AND MANAGEMENT},
	volume = {33},
	unique-id = {35638375},
	issn = {2210-9706},
	abstract = {The real-time railway traffic management problem occurs when the pre-planned timetable
		 cannot be kept due to various disturbances; therefore, the trains must be rerouted, reordered,
		 and rescheduled. Optimizing the real-time railway traffic management aims to resolve conflicts,
		 minimizing the delay propagation or energy consumption. In one of our previous works,
		 the existing mixed-integer linear programming optimization models are extended considering
		 a safety-relevant issue of railway traffic management, the overlaps. However, solving the
		 extended model can be time-consuming in complex control areas and traffic situations involving
		 numerous trains. Therefore, we propose different computationally efficient multi-stage models
		 by decomposing the problem according to the rerouting, reordering, and rescheduling sub
		problems. First, a lightweight heuristic MILP model that provides a fast but sub-optimal solution
		 is given by reformulating the train delays into pair-wise interpretation. Second, we extend the
		 heuristic model to grant an optimal solution to the original problem faster than the existing
		 MILP formulations. The impact of the model decomposition is investigated mathematically and
		 experimentally in various realistic simulated traffic scenarios concerning the optimization’s
		 objective value and computational demand. The proposed multi-stage models significantly
		 decrease the optimization runtime of both the original and the extended railway traffic
		 management problems.},
	year = {2025},
	eissn = {2210-9714},
	orcid-numbers = {Lövétei, István Ferenc/0000-0002-3246-5596}
}

@inproceedings{MTMT:35169199,
	title = {Real-Time Rail Energy Consumption Minimization: Optimal Speed Profile Planning},
	url = {https://m2.mtmt.hu/api/publication/35169199},
	author = {Lindenmaier, László and Aradi, Szilárd and Lövétei, István Ferenc},
	booktitle = {18th IEEE International Symposium on Applied Computational Intelligence and Informatics SACI 2024 : Proceedings},
	doi = {10.1109/SACI60582.2024.10619839},
	unique-id = {35169199},
	abstract = {In rail traffic, the timetable must be re-planned in real-time when traffic is perturbed. Methods that optimally reroute and reschedule the trains to resolve this traffic management problem already exist. These optimization models usually focus on minimizing delays. However, energy consumption is a key to economical and sustainable transportation. In this paper, we propose a method that calculates optimal speed profiles to minimize the energy consumption of the trains after solving the rerouting and rescheduling problems with a conventional model. Using a simulation environment, the proposed method is evaluated in two different rail networks. According to the experimental results, the proposed model can decrease the overall energy consumption by more than 10% on average. © 2024 IEEE.},
	year = {2024},
	pages = {175-182},
	orcid-numbers = {Lövétei, István Ferenc/0000-0002-3246-5596}
}

@inproceedings{MTMT:34568718,
	title = {Runtime Performance Analysis of a MILP-Based Real-Time Railway Traffic Management Algorithm},
	url = {https://m2.mtmt.hu/api/publication/34568718},
	author = {Aradi, Szilárd and Lindenmaier, László and Lövétei, István Ferenc},
	booktitle = {IEEE 21st International Symposium on Intelligent Systems and Informatics (SISY 2023)},
	doi = {10.1109/SISY60376.2023.10417744},
	unique-id = {34568718},
	abstract = {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. © 2023 IEEE.},
	keywords = {Optimization; intelligent systems; Monte Carlo methods; Linear programming; Integer programming; Optimisations; Runtimes; Railroads; Performance analysis; Runtime; Railroad transportation; Railway traffic management; rail transportation; Rails; Real- time; railway safety; Management problems; Performances analysis; Linear-programming; Runtime performance},
	year = {2023},
	pages = {000265-000270},
	orcid-numbers = {Lövétei, István Ferenc/0000-0002-3246-5596}
}

@article{MTMT:33723066,
	title = {Biztonság (safety) az elektronikus rendszerek fejlesztésében - A prolan Zrt. megoldása a PRORIS biztosítóberendezés fejlesztése során},
	url = {https://m2.mtmt.hu/api/publication/33723066},
	author = {Lantos, Péter and Lövétei, István Ferenc and Majzik, István},
	journal-iso = {VASÚTI VEZETÉKVILÁG},
	journal = {VASÚTI VEZETÉKVILÁG},
	volume = {2023},
	unique-id = {33723066},
	issn = {2559-8961},
	year = {2023},
	pages = {3-10}
}

@article{MTMT:33203516,
	title = {Valós idejű forgalmi konfliktus feloldása matematikai optimalizációval},
	url = {https://m2.mtmt.hu/api/publication/33203516},
	author = {Aradi, Szilárd and Lövétei, István Ferenc},
	journal-iso = {VASÚTI VEZETÉKVILÁG},
	journal = {VASÚTI VEZETÉKVILÁG},
	volume = {2022},
	unique-id = {33203516},
	issn = {2559-8961},
	year = {2022},
	pages = {22-28}
}

@CONFERENCE{MTMT:34041284,
	title = {Multi-Agent Deep Reinforcement Learning (MADRL) for Solving Real-Time Railway Rescheduling Problem},
	url = {https://m2.mtmt.hu/api/publication/34041284},
	author = {Kővári, Bálint and Lövétei, István Ferenc and Aradi, Szilárd and Bécsi, Tamás},
	booktitle = {Proceedings of the Fifth International Conference on Railway Technology: Research, Development and Maintenance},
	doi = {10.4203/ccc.1.23.5},
	unique-id = {34041284},
	year = {2022},
	orcid-numbers = {Lövétei, István Ferenc/0000-0002-3246-5596; Bécsi, Tamás/0000-0002-1487-9672}
}

@misc{MTMT:33117592,
	title = {Efficient Real-time Rail Traffic Optimization: Decomposition of Rerouting, Reordering, and Rescheduling Problem},
	url = {https://m2.mtmt.hu/api/publication/33117592},
	author = {Lindenmaier, László and Lövétei, István Ferenc and Aradi, Szilárd},
	unique-id = {33117592},
	abstract = {The railway timetables are designed in an optimal manner to maximize the capacity usage of the infrastructure concerning different objectives besides avoiding conflicts. The real-time railway traffic management problem occurs when the pre-planned timetable cannot be fulfilled due to various disturbances; therefore, the trains must be rerouted, reordered, and rescheduled. Optimizing the real-time railway traffic management aims to resolve the conflicts minimizing the delay propagation or even the energy consumption. In this paper, the existing mixed-integer linear programming optimization models are extended considering a safety-relevant issue of railway traffic management, the overlaps. However, solving the resulting model can be time-consuming in complex control areas and traffic situations involving many trains. Therefore, we propose different runtime efficient multi-stage heuristic models by decomposing the original problem. The impact of the model decomposition is investigated mathematically and experimentally in different rail networks and various simulated traffic scenarios concerning the objective value and the computational demand of the optimization. Besides providing a more realistic solution for the traffic management problem, the proposed multi-stage models significantly decrease the optimization runtime.},
	year = {2022}
}

@inproceedings{MTMT:33266689,
	title = {MILP-Based Optimization of the Extended Real- Time Railway Traffic Management Problem},
	url = {https://m2.mtmt.hu/api/publication/33266689},
	author = {Lindenmaier, László and Aradi, Szilárd and Bécsi, Tamás and Lövétei, István Ferenc},
	booktitle = {IEEE 16th International Symposium on Applied Computational Intelligence and Informatics SACI 2022},
	doi = {10.1109/SACI55618.2022.9919542},
	unique-id = {33266689},
	year = {2022},
	pages = {105-110},
	orcid-numbers = {Bécsi, Tamás/0000-0002-1487-9672; Lövétei, István Ferenc/0000-0002-3246-5596}
}

@article{MTMT:32801249,
	title = {Environment Representations of Railway Infrastructure for Reinforcement Learning-Based Traffic Control},
	url = {https://m2.mtmt.hu/api/publication/32801249},
	author = {Lövétei, István Ferenc and Kővári, Bálint and Bécsi, Tamás and Aradi, Szilárd},
	doi = {10.3390/app12094465},
	journal-iso = {APPL SCI-BASEL},
	journal = {APPLIED SCIENCES-BASEL},
	volume = {12},
	unique-id = {32801249},
	abstract = {The real-time railway rescheduling problem is a crucial challenge for human operators since many factors have to be considered during decision making, from the positions and velocities of the vehicles to the different regulations of the individual railway companies. Thanks to that, human operators cannot be expected to provide optimal decisions in a particular situation. Based on the recent successes of multi-agent deep reinforcement learning in challenging control problems, it seems like a suitable choice for such a domain. Consequently, this paper proposes a multi-agent deep reinforcement learning-based approach with different state representational choices to solve the real-time railway rescheduling problem. Furthermore, comparing different methods, the proposed learning-based approaches outperform their competitions, such as the Monte Carlo tree search algorithm, which is utilized as a model-based planner, and also other learning-based methods that utilize different abstractions. The results show that the proposed representation has more significant generalization potential and provides superior performance.},
	year = {2022},
	eissn = {2076-3417},
	orcid-numbers = {Lövétei, István Ferenc/0000-0002-3246-5596; Bécsi, Tamás/0000-0002-1487-9672}
}

@article{MTMT:32632491,
	title = {Erratum: Infrastructure modeling and optimization to solve real-time railway traffic management problems (Periodica Polytechnica Transportation Engineering (2021) 49:3 (270-282) DOI: 10.3311/PPtr.18582)},
	url = {https://m2.mtmt.hu/api/publication/32632491},
	author = {Lindenmaier, László and Lövétei, István Ferenc and Lukács, Gábor and Aradi, Szilárd},
	doi = {10.3311/PPTR.19186},
	journal-iso = {PERIOD POLYTECH TRANSP ENG},
	journal = {PERIODICA POLYTECHNICA TRANSPORTATION ENGINEERING},
	volume = {49},
	unique-id = {32632491},
	issn = {0303-7800},
	abstract = {When the above article was first published online some symbols in the text on pages 274-276, Table 7 on page 277, furthermore the subscript of the symbol bs in Eqs. (10), (11) and in the text on page 277 were incorrect. This has now been corrected in the online version. The correct version of some symbols in the text on pages 274-276, Table 7 on page 277, furthermore the subscript of the symbol bs in Eqs. (10), (11) and in the text on page 277 were published in this paper. © 2021 Budapest University of Technology and Economics. All rights reserved.},
	year = {2021},
	eissn = {1587-3811},
	pages = {308-308}
}