Title:	CAPMO-Train-and-related-projects
DNr:	NAISS 2023/5-499
Project Type:	NAISS Medium Compute
Principal Investigator:	Christiane Schmidt <christiane.schmidt@liu.se>
Affiliation:	Linköpings universitet
Duration:	2023-11-30 – 2024-06-01
Classification:	20105
Keywords:

Abstract

In this project, we aim to illuminate the possibilities of automated, optimized train dispatcher shifts that take all legal and operational restrictions into account and integrate train dispatcher workload. We will develop upper (and lower) bounds for the desired train dispatcher workload—as over- or undercutting those can impact attention and situational awareness. Moreover, we will study the effects of predictable but stochastically varying events on train dispatcher workload. Together with legal and operational requirements for train dispatcher shifts, these workload measures will build the basis for an optimization framework for the shifts. This framework will enable us to compute optimal shift plans: • Optimal tactical shift plans taking knowledge of forthcoming situations, that is, the current timetable and maintenance plan, into account • Optimally ad-hoc replanned shift plans (operational) when predictable but stochastically varying events occur during a work shift • Optimal tactical shift plans with stochastically integrated predictable but stochastically varying events The overall goal of this project is to enable Trafikverket to automatically find cost-effective and safe train dispatcher shifts and to operationally replan in case of unforeseen events. The optimal tactical shift plan delivered by this project will be compared to the current shift plan. However, the discrepancy between the plans is hard to predict. It will be discussed with the responsible management in Malmö with the purpose of clarifying how the new shift plans could be used in practice. The development of a tool for tactical shift planning based on the optimization framework is out of the scope of this project. That is, within this project we will develop methods and programs that can be used by researchers/experts and which we will use to produce solutions for exemplary problems. However, we will not develop a tool that Trafikverket can use in its current planning (which would require data bases, a well-developed graphical user interface etc.). But we will discuss the optimal tactical shift plans with operational experts to include as many real-world conditions as possible. This will lay out a possible way ahead for an implementation.