Public defence in Computer Science, M.Sc. Matti Huotari

Title of the doctoral thesis: Machine Learning Applications for Energy Utilization of Smart Buildings
Doctor's hat

Opponent: Professor Dante Barone, Federal University of Rio Grande do Sul, Brazil
Opponent: Professor Jukka Nurminen, University of Helsinki, Finland
Custos: Adjunct Professor Kary Främling, Aalto University School of Science, Department of Computer Science

The public defence will be organised on campus.

The thesis is publicly displayed 10 days before the defence in the publication archive Aaltodoc of Aalto University.

Electronic thesis

Public defence announcement:

AI applications for energy utilization of smart buildings

Energy utilization of smart buildings deals with issues of energy utilization directly while simultaneously taking into account the user-comfort, security and malfunctions. Our research aimed at integrating disparate energy components into coherent energy systems in buildings with the help of artificial intelligence. Given the risen number of renewable energy sources together with tightened regulation to energy consumption, the smart building energy applications provide means to combine new technology together with heterogeneous requirements and goals for energy utilization in buildings. We gave an overview of these goals that, in short, consist of optimal scheduling of energy consumption and production, optimization of costs, integration of renewable energy, user-behavior recognition, and consumer comfort. Then we proposed several new AI applications. Our case-study results provide means to forecast the equipment degradation for energy storage (battery packs), make estimations in a novel manner under uncertainty (gaps or a limited number of observations) for an air handling unit, and involve people in personal environmental comfort. These results are directly usable as models, or indirectly provide elements for artificial intelligence solutions for smart buildings. Provided that the obstacles for collecting data are overcome, the results also indicated that there is ample room for making and using applications for smart buildings with, for example, the algorithms and application developed during this research.

Contact details of the doctoral student: [email protected]

  • Published:
  • Updated:
URL copied!