Master Thesis - Physics-Informed Machine Learning for Dynamic Power System Characterization

Master Thesis - Physics-Informed Machine Learning for Dynamic Power System Characterization At the Institute of Climate and Energy Systems Engineering (ICE-1) we focus on the development of models and algorithms for simulation and optimization of decentralized, integrated energy systems. Such systems are characterized by high shares of renewable energies and increasing sector coupling, which leads to high spatial and temporal variability of energy supply and demand as well as a high degree of interdependence of material and energy flows.

Our research at the ICE institute aims to provide scalable and faster-than-real-time capable methods and tools that enable the energy-optimal, cost-efficient and safe design and operation of future energy systems. Your Job The transition toward renewable and converter-interfaced energy resources is creating increasingly fast and complex dynamics in modern power systems.

In this Master’s thesis, you will develop a physics-informed digital-twinning approach to better characterize these dynamics and estimate relevant electrical and control parameters from transient voltage and current data. Your tasks will include: Developing and analyzing representat