Startseite // SnT // Research // SerVal // Projects // Soft landing Design and Implementation for Innovative Building Operation

Built4U: Soft landing Design and Implementation for Innovative Building Operation

Project title: Built4U: Soft landing Design and Implementation for Innovative Building Operation
Principal investigator: Prof. Yves Le Traon
Vice principal investigators: Dr. Jacques Klein and Dr. Tegawende Bissyande
Partner: Paul Wurth S.A.
Funding: Industrial Funding
Research team: Dr. Jacques Klein, Dr. Tegawendé F. Bissyandé and Daoyuan Li
Industrial collaborators: Dr. Anne-Marie Solvi, Ben Muller and Paul Schummer
Starting date and Duration: 01.01.2015 to 31.12.2018
Contact person: Dr. Jacques Klein

Today a significant fraction of total energy consumption is attributed to the buildings sector. In order to save energy and protect the environment, energy consumption in buildings must be more efficient. At the same time, buildings should offer the same (if not more) comfort to their occupants. Consequently, modern buildings have been equipped with various sensors and actuators and interconnected control systems to meet occupants’ requirements. However, so far BAS data have not been well-exploited due to technical and cost limitations. Thus it can be exceptionally beneficial to take full advantage of the data flowing inside buildings in order to diagnose issues, explore solutions and improve occupant-building interactions.

This project aims at lowering the energy footprints of modern buildings by taking advantage of various data flowing within these buildings and enabling smarter control based on existing infrastructure. To that end, this project tries to investigate the possibility and feasibility of a plug- and-play and holistic data mining framework for smart buildings to collect, store, visualize and mine useful information and domain knowledge from data in smart buildings. The outcome of this project will allow non-technical experts to easily explore and understand their buildings with minimum IT support. The architecture of such a framework is illustrated in the figure below.

Specifically, this project will explore time series mining techniques to model patterns as well as outliers in the context of smart buildings. For instance, using time series classification can help profile the energy consumption of electric appliances, so that better energy usage maybe planned. Besides, (hierarchical) time series clustering techniques can be used to find outliers that are not in line with peer readings. Finally, autoregressive integrated moving average (ARIMA) can fit time series data into models represented as coefficients in order to provide a better understanding of the data or to predict future data points.