© AdobeStock/denbelitsky
Funding: Federal Ministry of Education and Research (Bundesministerium für Bildung und Forschung, BMBF)
Abstract: The research project EKSSE aims to enhance the energy efficiency of German underground rail transport, reduce costs, and contribute to sustainable mobility through real-time coordination of train operations. Goals include lowering overall power demand, increasing the regenerative braking energy feed-in ratio, and reducing peak power demands. The unique challenge involves a discrete-continuous coupling of optimal control approaches and real-time schedule optimization. The developed procedure uses machine learning to identify delay patterns, incorporates forecasts into real-time optimization, and dynamically adjusts train travel and dwell times. Input-output energy-based models and network coupling are employed, considering uncertainties. The overall optimization procedure, including real-time adaptive solution algorithms, is implemented in a software demonstrator, moving towards a digital twin of the underground train system for significant energy consumption reduction.
Project page at Fraunhofer SCS
Max Engelhardt, Doctoral Researcher
max.engelhardt@utn.de, +49 911 9274-1605
Tobias Kuen, Doctoral Researcher
tobias.kuen@iis.fraunhofer.de, +49 911 58061-9571