Izvorni znanstveni članak
https://doi.org/10.7307/ptt.v38i1.1201
Intelligent Train Timetable Generation Technology Based on Monte Carlo Tree Search Algorithm
Junyuan HE
; School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China; CR Train Working Diagram Technology Centre, China Academy of Railway Sciences Corporation Limited, Beijing, China; Transportation & Economics Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing, China
Zhangdui ZHONG
; School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
*
Bo LI
; CR Train Working Diagram Technology Centre, China Academy of Railway Sciences Corporation Limited, Beijing, China; Transportation & Economics Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing, China
Jiaming FAN
; CR Train Working Diagram Technology Centre, China Academy of Railway Sciences Corporation Limited, Beijing, China; Transportation & Economics Research Institute, China Academy of Railway Sciences Corporation Limited, Beijing, China
Jianwen DING
; School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
Wei CHEN
; School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
* Dopisni autor.
Sažetak
This paper presents an innovative approach to train timetable generation using Monte Carlo tree search (MCTS) integrated with a deep reinforcement learning technique. The generation and adjustment of train timetables for high-speed railways represent a complex optimisation problem with numerous rule-based constraints that traditional mathematical methods struggle to solve efficiently. Therefore, the train timetable generation problem is modelled as a discrete spatiotemporal Markov decision process, and a comprehensive MCTS-based algorithm is developed to effectively balance exploration and exploitation through a structured tree search mechanism. The result of the comparative analysis demonstrates that MCTS-based algorithms significantly outperform state-of-the-art reinforcement learning algorithms, including double deep Q-network (DDQN) and proximal policy optimisation (PPO), achieving optimal solutions 6.5 times faster with superior training stability. To validate the scalability and real-world applicability, a large-scale case study involving 120 pairs of trains on the Beijing-Shanghai High-Speed Rail corridor over an 18-hour period successfully resolved all 45,600 initial conflicts. The optimised timetables yield significant operational improvements, including a 16.4% reduction in average delay time, 22.8% improvement in track utilisation efficiency and 9.7% reduction in energy consumption. This research contributes to the advancement of intelligent railway operations optimisation and demonstrates the potential of MCTS-based approaches to transform complex transportation problems.
Ključne riječi
Monte Carlo tree search; high-speed railway; train timetable intelligence; deep reinforcement learning; Markov decision process
Hrčak ID:
343943
URI
Datum izdavanja:
29.1.2026.
Posjeta: 332 *