Intelligent Optimization Strategy for Shunting Operation Efficiency at Railway Stations Based on Deep Reinforcement Learning and Infrastructure Upgrading
Shunting operation is the core link of railway station transportation organization, whose efficiency directly determines the turnover speed of trains, the utilization rate of station facilities and the overall operational efficiency of the railway network. With the rapid growth of rail freight and passenger transport volume, the traditional shunting operation mode, which relies on manual experience and backward equipment, has been difficult to adapt to the demand of modern railway intelligent development. To solve the problems of low efficiency, high labor intensity and poor real-time adaptability in current shunting operations, this paper systematically analyzes the key influencing factors of shunting efficiency from four dimensions: operation organization, equipment status, personnel quality and intelligent technology application. Based on the real operation data of 12 typical railway stations (6 freight stations, 4 passenger stations, 2 marshalling stations) in China, Kazakhstan and Uzbekistan surveyed from January 2024 to June 2024 and typical railway stations at home and abroad, combined with deep reinforcement learning (DRL), 5G Beidou positioning and other advanced technologies, this paper proposes a multi-dimensional integrated optimization strategy for shunting operation efficiency. The experimental verification is carried out through live deployment for 6 months at Huanghua Port Station (China) and a large freight train depot in Kazakhstan. The results show that the proposed strategy can effectively reduce the number of shunting hooks, shorten the operation time and improve the utilization rate of shunting locomotives. The research results provide a practical and feasible technical path for the intelligent upgrading of shunting operations and the improvement of operation efficiency, which has important theoretical and engineering application value for promoting the high-quality development of railway transportation.
Cite this paper
Liu, S. , Cheng, H. , Zhuo, S. , He, A. , Zhou, J. , Guo, Y. and Zheng, D. (2026). Intelligent Optimization Strategy for Shunting Operation Efficiency at Railway Stations Based on Deep Reinforcement Learning and Infrastructure Upgrading. Open Access Library Journal, 13, e15150. doi: http://dx.doi.org/10.4236/oalib.1115150.
Qiu, J., Xu, S., Tang, M., Liu, J. and Song, H. (2025) Optimization of Shunting Operation Plan in Large Freight Train Depot Based on DQN Algorithm. PLOS ONE, 20, e0320762. https://doi.org/10.1371/journal.pone.0320762
Suyunbayev, S., Khusenov, U., Khudayberganov, S., Jumayev, S. and Kayumov, S. (2023) Im-proving Use of Shunting Locomotives Based on Changes in Infrastructure of Railway Station. E3S Web of Conferences, 365, Article No. 05011. https://doi.org/10.1051/e3sconf/202336505011
Bakyt, G., Makhanova, A., Mussabekov, M., Ashirbayev, G., Zhamankulov, M., Sarsenov, K., et al. (2025) Methodology for Assessing the Key Operational Efficiency Indicators for Removal and Shunting Operations of Shunting Locomotives. Communica-tions—Scientific letters of the University of Zilina, 27, B250-B260. https://doi.org/10.26552/com.c.2025.048
Zhao, W., Zhou, L. and Han, C. (2025) A Hybrid Optimization Approach Combining Rolling Horizon with Deep-Learning-Embedded NSGA-II Algorithm for High-Speed Railway Train Rescheduling under Interruption Conditions. Sustainability, 17, Article No. 2375. https://doi.org/10.3390/su17062375
Saeednia, M., Bruckmann, D. and Weidmann, U. (2015) Event-Based Model for Optimizing Shunting Yard Operations. Transportation Research Record: Journal of the Transportation Re-search Board, 2475, 90-94. https://doi.org/10.3141/2475-11
Yu, T. (2022) Quality Analysis of Railroad Train Shunting Operation Plan Using the Intelligent Body Model. Advances in Multimedia, 2022, Article ID: 4441369. https://doi.org/10.1155/2022/4441369
Demiridis, N. and Pyrgidis, C. (2022) Getting Freight Trains Back on Track—How Railway Undertakings, In-frastructure Owners and Regulators Can Navigate the Main Dilemmas in Freight Business to Drive Sustainable Growth. Frontiers in Sustainability, 3, Article ID: 903945. https://doi.org/10.3389/frsus.2022.903945
Wu, Y., He, S., Long, Z. and Tang, H. (2025) Integrated Operations Scheduling and Resource Allocation at Heavy Haul Railway Port Stations: A Collaborative Dual-Agent Ac-tor-Critic Reinforcement Learning Framework. Systems, 13, Article No. 762. https://doi.org/10.3390/systems13090762
Li, X., He, H., Yang, Y. and Fan, Z. (2025) Automatic Search Model of Railway Shunting Route Based on Improved Artificial Neural Network Algorithm. Discover Artificial Intelligence, 5, Article No. 231. https://doi.org/10.1007/s44163-025-00484-6
Zhong, M., Yue, Y., Zhou, L. and Zhu, J. (2024) Parallel Optimization Method of Train Scheduling and Shunting at Complex High-Speed Railway Stations. Comput-er-Aided Civil and Infrastructure Engineering, 39, 731-755. https://doi.org/10.1111/mice.13077
Zhang, Y., Hu, R., Zeng, Q., Wang, Y., Liu, Y. and Huang, S. (2023) Optimal Train Platforming with Shunting Oper-ations for Multidirectional Passenger Stations: A Case Study of Guangzhou Sta-tion. Mathematics, 11, Article No. 3136. https://doi.org/10.3390/math11143136
