A State Reduction Approach for Learning-Based Model Predictive Control for Train Rescheduling

Reference

C. F. O. da Silva, X. Liu, A. Dabiri, and B. De Schutter, "A state reduction approach for learning-based model predictive control for train rescheduling," Proceedings of the 1st IFAC Joint Conference on Computers, Cognition, and Communication (J3C 2025), Padova, Italy, pp. 383-388, Sept. 2025.

Abstract

This paper proposes a state reduction method for learning-based model predictive control (MPC) for train rescheduling in urban rail transit systems. The state reduction integrates into a control framework where the discrete decision variables are determined by a learning-based classifier and the continuous decision variables are computed by MPC. Herein, the state representation is designed separately for each component of the control framework. While a reduced state is employed for learning, a full state is used in MPC. Simulations on a large-scale train network highlight the effectiveness of the state reduction mechanism in improving the performance and reducing the memory usage.

Publisher page

• Access full text  

Downloads

• PDF of corresponding technical report (742 KB)

BibTeX

@inproceedings{DaSLiu:25-018,
   author    = {da Silva, Caio Fabio Oliveira and Liu, Xiaoyu and Dabiri, Azita
                and De Schutter, Bart},
   title     = {A State Reduction Approach for Learning-Based Model Predictive
                Control for Train Rescheduling},
   booktitle = {Proceedings of the 1st IFAC Joint Conference on Computers,
                Cognition, and Communication (J3C 2025)},
   address   = {Padova, Italy},
   pages     = {383--388},
   month     = sep,
   year      = {2025}
   }

• Download BibTeX entry