Zhang, Zhiqing (Tsinghua University), Wang, Chong (Tsinghua University), Li, Zhongcan (Tsinghua University), Dong, Wei (Tsinghua University), Yan, Xiang (CRSC Research & Design Institute Group Co.,Ltd.), Long, Zhao (CRSC Research & Design Institute Group Co.,Ltd.), Sun, Xinya (Tsinghua University)

An Optimization Method of Marshalling Station Period Scheduling Plan based on Ordinal Optimization

Scheduled for presentation during the Regular Session "S33a-Intelligent Control for Next-Generation Railway Systems" (FR-LM-T33), Friday, November 21, 2025, 11:10−11:30, Southport 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Marshalling stations are critical hubs in railway freight networks, where optimizing the period scheduling plan is paramount for overall operational efficiency. Traditional mathematical programming methods suffer from combinatorial explosion, rendering them impracticable in complex real-world scenarios. Although traditional heuristic algorithms can be used in complex real-world scenarios, it is difficult to evaluate the quality of solutions and simulation evaluation requires considerable computing resources and time. To address these issues, this paper applies the ordinal optimization(OO) method to optimize the period scheduling plan of marshalling stations(PSPMS) and proposes an optimization method of PSPMS based on OO(PSPMS-OO). This method uses the crude simulation model with faster running speed to evaluate the optimization objective of solutions so as to greatly improve the solving efficiency. Based on the OO theory, the quality of solutions is guaranteed and the quantitative evaluation for the quality of solutions is realized. Simulation experiments using the real-world data from a typical Chinese marshalling station demonstrate that PSPMSOO achieves solution quality the same as that of an optimization method of PSPMS based on genetic algorithm(PSPMS-GA), while reducing the solving time by 81.05%. Furthermore, solutions obtained by PSPMS-OO are guaranteed to be within the top 5% feasible uniform sampling solutions at 95% confidence.