Data Driven Predictive Control for Smart Buildings

A Ph.D. project studying and developing modern data driven predictive control algorithms to increase the efficiency of smart buildings.

New technologies for signal processing and control have great potential to increase efficiency of smart buildings. It could be to save energy, increase living comfort, reduce maintenance, or improve management. In this project we will in particular study and develop modern data driven predictive control algorithms. These methods rely on a mix of linear systems theory, optimization, and machine learning. They have proven to be efficient for complex systems with time varying dynamics where it is difficult to maintain accurate models.


This Ph.D. project will be carried out within the framework of the Dig-It Lab competence center in tight collaboration with industrial partners and as part of a multidisciplinary team of researchers. We will review existing state of the art, the application needs, and select promising candidate control approaches. We will further adapt and develop the technology and theoretical understanding for the purposes of interest.

Project contact

Magnus Jansson

Division of Information Science and Engineering, School of Electrical Engineering and Computer Science