Leandro Von Krannichfeldt

Expertise Energy forecasting, Signal Processing, Learning Algorithms Leandro obtained his master's degree in Electrical Engineering and Information Technology from ETH Zürich. Before joining the Intelligent Maintenance and Operation Systems Laboratory, his research focused on energy demand and generation forecasting as well as collaborative learning. During the course of his Ph.D. study, he will explore hybrid digital twins for energy performance optimization in a joint project with the Urban Energy System Laboratory at the Swiss Federal Laboratories for Materials Science and Technology ResearchHybrid Digital Twins for Building Energy Systems The operation of buildings is responsible for 30% of energy consumption and 26% of CO2emissions worldwide. Increasing digitalization and use of sensors hold great potential forconstructing digital twins for building operation optimizations. A digital twin is a continuouslymonitored digital replica of the physical building, capable of forecasting future states andsuggesting control actions for more efficient operation. The foundation of a digital twin forbuilding energy optimization is based on the Building Energy Model (BEM), a digital model usedfor building energy analysis and prediction.In building energy modeling, three major challenges related to data availability persist. First,data scarcity is a common issue for newly built or newly equipped buildings with sensors, asthere may be insufficient data collected post-installation to develop a reliable model. Second,after model development, newly incoming sensor data can alleviate data scarcity but poseschallenges for updating the model. Third, the unique sensor configuration in each buildingcomplicates a unified exploitation of traditional building energy modeling, given that buildingsmay not have the same number or types of sensors due to costs or equipment constraints.This Ph.D. project aims to address these challenges by combining data-driven methodologieswith physics-based modeling into hybrid models to exploit their respective advantages. Teaching & PhDCIVIL-226 Introduction to Machine Learning for EngineersCIVIL-426 Machine learning for predictive maintenance applicationsOpen Student Projects If you are a student interested in one of the following projects, please get in touch:Large-scale Building Energy Modeling by Combining Physics-based and Data-driven ModelingInvestigating Basic Capabilities of Time Series Forecasting Foundation Models