hybrid-models federated-learning


Within this project AI-based building models are developed to solve the problem of peak loads in energy demands caused by renewable energy sources.

By 2050, the entire built environment must be energy neutral. In addition, by 2050 all homes and utility buildings must be "off the gas grid". The energy transition leads to peak loads in terms of energy demand. The building models play a central role in optimizing energy consumption at building level, and (more importantly) in balancing energy supply and demand at district level. The AI based models are therefore essential in facilitating the energy transition and the transition to an energy-neutral built environment. However, the AI based models use data which is considered to be private. Therefore, the technique Federated Learning is used to be able to learn from the energy uage data whilst protecting the privacy of individuals.

The main research objective is to develop a building model which combines physics knowledge model with a machine learning model. This model will be suitable for predicting energy demand and scalable for all types of building types expected in a smart district.


  • Madelon Molhoek, Consultant Data Science, e-mail: