Improving the quality of railway dispatching tasks via agent-based simulation

Unavoidable disturbances induce the necessity of operations control and dispatching tasks in the timetable-driven rail traffic. Therefore, dispatching becomes one of the most relevant challenges for economic success, since it directly affects the timeliness of passengers, which is a core indicator of customer satisfaction. Thus, the integration of passenger preferences into dispatching strategies is a reasonable extension of conventional dispatching algorithms. In this paper we present an agent-based simulation system for Deutsche Bahn AG modelling the complete German railway network with about 30,000 trains and millions of passengers per day. With this system various dispatching strategies considering passenger information and aiming to reduce passenger waiting times have been tested. We show that even simple heuristics achieve better results than the rule based dispatching strategies currently in use. Further improvements, qualitative as well as quantitative, are induced by an online re-routing algorithm which efficiently computes new routes for passengers affected by missed connections.