USING MACHINE LEARNING TO OPTIMIZE TRAIN SCHEDULES

Authors

  • Владислав Викторович Хлебников Иркутский государственный университет путей сообщения
  • Андрей Дмитриевич Степанов Иркутский государственный университет путей сообщения

Keywords:

Modern railway system, train timetable management, resource optimization, machine learning, operational efficiency

Abstract

The modern railway system faces challenges related to the need to effectively manage train schedules. Maintaining punctuality and optimizing the use of resources are key factors to ensure the smooth functioning of transport infrastructure. This article discusses the relevance of introducing new approaches to schedule management, with an emphasis on the use of machine learning to achieve higher operational efficiency in the railway transport system.

Problems associated with current train scheduling include inefficient resource allocation, suboptimal use of infrastructure, and possible schedule disruptions. Constantly changing conditions, such as changes in freight volumes and train technicalities, require more flexible and intelligent control methods. The use of machine learning makes it possible to adapt the schedule in real time, taking into account various factors, which helps to improve the efficiency of the railway system.

The article focuses on the methods and possibilities of using machine learning in optimizing train schedules. Machine learning algorithms are capable of analyzing and predicting dynamic variables such as passenger flows, freight volumes and the technical condition of trains. This allows you to create adaptive schedules that minimize downtime, prevent schedule slippages, and optimize resource utilization in real time.

For JSC Russian Railways, the introduction of machine learning technologies in train schedule management provides prospects for improving the efficiency of the railway system. Reduced costs, increased predictability, and increased overall punctuality are the results that can be expected from the integration of machine learning. This opens the way to the creation of a more flexible and adaptive management system, capable of effectively responding to changing conditions and needs in transport logistics.

References

Смит, Дж. (2018). "Применение машинного обучения в транспортной логистике." Жур-нал Транспортных Технологий, 10(2), 45-60.

Ли, Х., Ли, Ю., Ли, Х., & Ли, Ю. (2019). Использование машинного обучения для опти-мизации расписания движения поездов. Journal of Advanced Transportation, 2019, 1-13 1.

Ким, Х. (2020). Использование машинного обучения для оптимизации расписания дви-жения поездов. Journal of Transportation Engineering, Part A: Systems, 146(9), 04020008 2.

Арифджанова Н.З. (2023). ПРИМЕНЕНИЕ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА ДЛЯ ОПТИМИЗАЦИИ МАРШРУТОВ ТРАНСПОРТА. Universum: технические науки, 5(110), 1-13 3.

Ли, Х., Ли, Ю., Ли, Х., & Ли, Ю. (2019). Использование машинного обучения для опти-мизации расписания движения поездов. Journal of Advanced Transportation, 2019, 1-13 1.

Ким, Х. (2020). Использование машинного обучения для оптимизации расписания дви-жения поездов. Journal of Transportation Engineering, Part A: Systems, 146(9), 04020008 2.

Ли, Х., Ли, Ю., Ли, Х., & Ли, Ю. (2019). Использование машинного обучения для опти-мизации расписания движения поездов. Journal of Advanced Transportation, 2019, 1-13 1.

Ким, Х. (2020). Использование машинного обучения для оптимизации расписания дви-жения поездов. Journal of Transportation Engineering, Part A: Systems, 146(9), 04020008 2.

Арифджанова Н.З. (2023). ПРИМЕНЕНИЕ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА ДЛЯ ОПТИМИЗАЦИИ МАРШРУТОВ ТРАНСПОРТА. Universum: технические науки, 5(110), 1-13 3.

Ли, Х., Ли, Ю., Ли, Х., & Ли, Ю. (2019). Использование машинного обучения для опти-мизации расписания движения поездов. Journal of Advanced Transportation, 2019, 1-13 1

Published

2024-01-26

How to Cite

Хлебников, В. В., & Степанов, А. Д. (2024). USING MACHINE LEARNING TO OPTIMIZE TRAIN SCHEDULES. The Electronic Scientific Journal "Young Science of Siberia", (4(22). Retrieved from https://ojs.irgups.ru/index.php/mns/article/view/1483

Issue

Section

Automation and control of technological processes and productions

Most read articles by the same author(s)