PANDA: a software tool for improved train dispatching with focus on passenger flows

We introduce the decision support tool PANDA (Passenger Aware Novel Dispatching Assistance). Our web-based tool is designed to provide train dispatchers with detailed real-time information about the current passenger flow and the multidimensional impact of waiting decisions in case of train delays. After presenting the algorithmic background and PANDA’s main features, we show how it can be utilized in a typical use case scenario for train dispatchers. Besides its practical value for train dispatchers, the framework can be used to systematically study scientific questions. Exemplarily, we use our software to experimentally analyse the influence of waiting decisions on realistic passenger flows of Deutsche Bahn. In a first experiment, we evaluate PANDA’s potential benefit for passengers. Our findings indicate that a remarkable reduction in total delay might be possible in comparison to current practice. In two additional experiments, we investigate the timing aspect of waiting decisions. Our observations suggest that the timing of waiting decisions is of crucial importance and that a carefully implemented early rerouting strategy has a significant potential to reduce resulting delays of passengers. & Ralf Rückert [email protected] Martin Lemnian [email protected] Christoph Blendinger [email protected] Steffen Rechner [email protected] Matthias Müller-Hannemann [email protected] 1 Institut für Informatik, Martin-Luther-Universität Halle-Wittenberg, Von-Seckendorff-Platz 1, 06120 Halle (Saale), Germany 2 DB Mobility Logistics AG, Hahnstraße 40, 60528 Frankfurt am Main, Germany 123 Public Transp DOI 10.1007/s12469-016-0140-0