Solving the train-platforming problem via a two-level Lagrangian Relaxation approach

TL;DR

This paper introduces a two-level Lagrangian Relaxation approach to optimize train platforming at busy high-speed railway stations, effectively balancing travel and deviation times with near-optimal solutions.

Contribution

It develops a novel two-level space-time network model and applies a two-level Lagrangian Relaxation method to efficiently solve complex station platforming problems.

Findings

The method achieves solutions within 2% of optimality on realistic instances.

It outperforms Logic-based Benders Decomposition in accuracy and speed.

Near-optimal solutions are obtained in very short computational times.

Abstract

High-speed railway stations are crucial junctions in high-speed railway networks. Compared to operations on the tracks between stations, trains have more routing possibilities within stations. As a result, track allocation at a station is relatively complicated. In this study, we aim to solve the train platforming problem for a busy high-speed railway station by considering comprehensive track resources and interlocking configurations. A two-level space-time network is constructed to capture infrastructure information at various levels of detail from both macroscopic and microscopic perspectives. Additionally, we propose a nonlinear programming model that minimizes a weighted sum of total travel time and total deviation time for trains at the station. We apply a Two-level Lagrangian Relaxation (2-L LR) to a linearized version of the model and demonstrate how this induces a decomposable train-specific path choice problem at the macroscopic level that is guided by Lagrange multipliers associated with microscopic resource capacity violation. As case studies, the proposed model and solution approach are applied to a small virtual railway station and a high-speed railway hub station located on the busiest high-speed railway line in China. Through a comparison of other approaches that include Logic-based Benders Decomposition (LBBD), we highlight the superiority of the proposed method; on realistic instances, the 2-L LR method finds solution that are, on average, approximately 2% from optimality. Finally, we test algorithm performance at the operational level and obtain near-optimal solutions, with optimality gaps of approximately 1%, in a very short time.