Prof. Dr. Florian Steinke

Prof. Dr. Florian Steinke
Landgraf-Georg-Str. 4
64283 Darmstadt

Building S3|10, Office: 306
Phone: +49 (0) 6151 16-21711
Telefax: +49 (0) 6151 16-21712


Research Interest

Applying algorithms and tools from machine learning, optimization, and control to energy management problems such as energy system design, energy system operation, and energy automation.

Short Bio

Florian Steinke is a full professor at TU Darmstadt and heads the Energy Information Networks & Systems lab since 2017.

Prior to this, he was with Siemens Corporate Technology, Automation & Control, in Munich from 2009-2017. He lead the development of a functional architecture & algorithms for an island grid control system with up to 100% renewables, lead the development for a multimodal energy system analysis & optimization tool for studying complete countries as well as specific hybrid energy projects, and contributed to several other research projects in the energy domain, but also for hearing aids, ore grinding mills, intelligent traffic control systems, and semantic web computing. In 2009, he received a PhD for his work at the Max-Planck-Institute for Biological Cybernetics, Tübingen (departement now in MPI for Intelligent Systems), in Machine Learning. In 2005, he obtained a Diploma degree in Computational Physics from the Eberhardt-Karls-Universität Tübingen

Since 2018, Florian Steinke is the spokesman of the profile area "Future Energy Systems" of the Technical University Darmstadt. He is a member of the IEEE/PES and the German engineering society VDE/ETG. He serves in the VDE/ETG working group V1 on Generation as well as two CIGRE's WGs on Power Systems Planning under Uncertainty and on Operating Strategies and Preparedness for System Operational Resilience. He received the DAGM Student Award for the best diploma thesis in pattern recognition in 2005 and the Siemens PG IE Innovation Award 2014 for his works on island grids.





Older Publications

A full list of past publications of Florian Steinke can be found here. A selection of older key contributions is:

Energy System Design

  • Steinke, F., P. Wolfrum and C. Hoffmann: Grid vs. storage in a 100% renewable Europe, Renewable Energy 50, 826-832, (2013) DOI  
  • Schaber, K., F. Steinke and T. Hamacher: Grid Extensions for the Integration of Variable Renewable Energies in Europe: Who Benefits Where?, Energy Policy 43, 123-135, (2012) DOI     
  • Knorr, K.; Zimmermann, B.; Kirchner, D.; Speckmann, M.; Spieckermann, R.; Widdel, M.; Wunderlich, M.; Mackensen, R.; Rohrig, K.; Steinke, F.; Wolfrum, P.; Leveringhaus, T.; Lager, T.; Hofmann, L.; Filzek, D.; Göbel, T.; Kusserow, B.; Nicklaus, L.; Ritter, P. (2014): Kombikraftwerk 2 / RegenerativKraftwerk 2050: Wege zu einer 100%-Versorgung mit erneuerbaren Energien - Abschlussbericht, Pilotprojekt unter Förderung des Bundesministeriums für Umwelt, Naturschutz und Reaktorsicherheit, (08 2014) Link

Energy Systems Operation

  • Kellerer, E., Steinke, F.: Scalable Economic Dispatch for Smart Distribution Networks, IEEE Transaction on Power Systems 30(4), 1739-1746, (2015) DOI     
  • U. Münz, M. Metzger, A. Szabo, F. Steinke, P. Wolfrum, R. Sollacher, D. Obradovic, M. Buhl, T. Lehmann, M. Duckheim, and S. Langemeyer: Overview of Control Technologies for Future Power Systems – An industry perspective, at - Automatisierungstechnik, 869–882, (2015) DOI     
  • Auer, S., F. Steinke, Chunsen, X., Sollacher, R. and Szabo, A.: Can Distribution Grids Significantly Contribute to Transmission Grids' Voltage Management?, IEEE PES Innovative Smart Grid Technologies, Europe (ISGT Europe 2016), Ljubljana, Slovenia (2016) DOI

Machine Learning

  • Steinke, F., M. Hein and B. Schölkopf: Non-parametric Regression between General Riemannian Manifolds, SIAM Journal on Imaging Sciences (SIIMS) 3(3), 527-563, (09 2010) PDF
  • Steinke, F. and B. Schölkopf: Kernels, Regularization and Differential Equations. Pattern Recognition 41(11), 3271-3286 (11 2008) PDF     
  • Steinke, F., M. Seeger and K. Tsuda: Experimental design for efficient identification of gene regulatory networks using sparse Bayesian models. BMC Systems Biology 1(51), 1-15 (11 2007) PDF


Print | Legal note | Privacy Policy | Sitemap | Search | Contact
to topto top