Synthetic data for a better understanding of residential energy demand

IMPORTANT: Please register through this webinar link before the event
👇👇👇
https://us02web.zoom.us/webinar/register/WN_UizheUSdTZqs717UvLFwjQ

Join the next Synthetic Data Meetup to learn how household energy demand can be simulated with high-quality synthetic behavioral data!

Hosted by: Dr. Paul Tiwald, Head of Data Science at MOSTLY AI

Guest speaker: Max Kleinebrahm, Research Assistant at the Chair of Energy Economics at the Karlsruhe Institute of Technology in Germany. His research interests are in renewable energies, analysis, and modeling decentralized energy systems, energy self-sufficient residential buildings, and time series analysis of energy consumption and occupant behavior. In his PhD, he is investigating the dissemination of self-sufficient residential buildings in the future European energy system. Max holds a Bachelor's and Master's degree in Industrial Engineering with a major in Mechanical Engineering/Power Engineering at the RWTH Aachen University and the Norwegian University of Science and Technology (NTNU).

The talk
Models simulating household energy demand based on occupant behavior have received increasing attention over the last years due to the need to better understand fundamental characteristics that shape the energy demand profile. In this presentation, methods from the field of deep learning are presented, which make it possible to capture complex long-term relationships in occupant behavior and are therefore able to provide high-quality synthetic behavioral data. The generated synthetic data set combines various advantages of individual empirically collected data sets and thus enables a better understanding of residential energy demand without collecting new data with great effort.