Learning-based model predictive control for passenger-oriented train rescheduling with flexible train composition

Xiaoyu Liu

doi:10.1016/j.trc.2026.105841

Learning-based model predictive control for passenger-oriented train rescheduling with flexible train composition

2026-07-01

2

PRE

AI

X

Xiaoyu Liu *

D

da Silva, Caio Fabio Oliveira

DOI：10.1016/j.trc.2026.105841

Original

Original request for help

Save

Abstract

En 中文

This paper focuses on passenger-oriented real-time train rescheduling, considering flexible train composition and rolling stock circulation, by integrating learning-based and optimization-based approaches. A learning-based model predictive control (MPC) approach is developed for realtime train rescheduling with flexible train composition and rolling stock circulation to address time-varying passenger demands. In the proposed approach, the values of the integer variables are obtained by pre-trained long short-term memory (LSTM) networks, while the continuous variables are determined through nonlinear constrained optimization. The learning-based MPC approach enables us to jointly consider efficiency and constraint satisfaction by combining learning-based and optimization-based approaches. In order to reduce the number of integer variables, four presolve techniques are developed to prune a subset of integer decision variables. Numerical simulations based on real-life data from the Beijing urban rail transit system are conducted to illustrate the effectiveness of the developed learning-based MPC approach.

Keywords:

Urban rail transit

Train rescheduling

Time-varying passenger demands

Model predictive control

Long short-term memory networks

Learning-based model predictive control for passenger-oriented train rescheduling with flexible train composition

Abstract

Journal

Organization

Cited Papers