Computational decision-support for railway traffic management and associated configuration challenges: An experimental study

Abstract

This paper investigates potential configuration challenges in the development of optimization-based computational re-scheduling support for railway traffic networks. The paper presents results from an experimental study on how the characteristics of different situations influence the problem formulation and the resulting re-scheduling solutions. Two alternative objective functions are applied: Minimization of the delays at the end stations which exceed 3 min and minimization of delays larger than 3 min at intermediary commercial stops and at end stations. The study focuses on the congested, single-tracked Iron Ore line located in Northern Sweden. A combinatorial optimization model adapted to the special restrictions of this line is applied on 20 different disturbance scenarios and solved using commercial optimization software. The resulting re-scheduling solutions are analyzed numerically and visually in order to better understand the practical impact of using the suggested problem formulations in this context. The results show that the two alternative, objective functions result in structurally, quite different re-scheduling solutions. All scenarios were solved to optimality within 1 min or less, which indicates that commercial solvers can handle practical problems of a relevant size for this type of setting, but the type of scenario has also a significant impact on the computation time.