eXplainable AI for electrcity and control prices
Numerous factors influence the prices of electricity and control power. We utilized the increasing amount of available data from energy systems to identify how certain generation types, load or fuel prices influence electricity prices or how legal changes affect prices.
Understanding electricity prices beyond the merit order principle using explainable AI, Julius Trebbien, Leonardo Rydin Gorjao, Aaron Praktiknjo, Benjamin Schäfer, Dirk Wirrhaut, Energy and AI, Volume 13, July 2023, 100250
Braess' paradox in power grids
Constructing new lines in power grids may reduce the system's performance. We proposed an approach for the prediction of edges lowering system performance and define potential constraints for grid extensions.
Understanding Braess’ Paradox in power grids, Benjamin Schäfer, Thiemo Pesch, Debsankha Manik, Julian Gollenstede, Guosong Lin, Hans-Peter Beck, Dirk Witthaut & Marc Timme, Nature Communications volume 13, Article number: 5396 (2022)
Paper Press release (in German)
Data-driven load profiles
In modern power grids, knowing the required electric power demand and its variations is necessary to balance demand and supply. We developed a data-driven approach to extract the trend and characterise demand fluctuations.
Data-driven load profiles and the dynamics of residential electricity consumption, Mehrnaz Anvari, Elisavet Proedrou, Benjamin Schäfer, Christian Beck, Holger Kantz & Marc Timme, Nature Communications volume 13, Article number: 4593 (2022)