Reduce Energy Consumption With Office Sensors - Scientific Research


Have you ever wondered that the occupancy of a building may be related to the unused potential for energy savings? Why is it important to optimize the control of heating, ventilation, and air conditioning systems?

The researchers of Vilnius Gediminas Technical University have conducted the employment surveys of administrative buildings by using TableAir workplace occupancy sensors. The large amounts of depersonalized data previously collected by the company were also used.

The Research was carried out as part of a project, “Research on the design and actual life cycle energy needs of a building to assess the impact of consumer behavior “ (No S-MIP-20-62), funded by the Research Council of Lithuania. Its results have been published in the article Office buildings occupancy analysis and prediction associated with the impact of the COVID-19 pandemic in the highly ranked international journal Sustainable Cities and Society.

The executor of the research Junior Researcher Jonas Bielskus compared TableAir sensors with 3D indoor occupancy cameras and other similar products available on the market and used in parallel. He concluded that the sensors produced by TableAir allow accurate and reliable detection of occupied workplaces thanks to the double-checking methodology. In addition, they are easily mounted; the information is transmitted to a server and can be read remotely.

Office sensor breakdown

Project Manager, Professor of the Department of Building Energetics, Doc. Dr. Violeta Motuzienė said that monitoring the building occupancy is related to the unused potential for energy savings in existing buildings. In this case, TableAir sensors provide the ability to store large amounts of data (BigData) that can be used to optimize the control of heating, ventilation, and air conditioning systems.

The scientists of Vilnius Tech used the data collected by TableAir sensors to develop a mathematical forecasting model for the occupancy of the administrative building. The machine learning-based model is able to use sensor data to train and forecast building occupancy. It enables the use of artificial intelligence to pre-optimize the control of heating, ventilation, and air conditioning systems. This is especially relevant in the optimization of energy needs of ventilation systems, where the occupancy of the premises directly determines the real demand for ventilation, and often over-ventilated premises (i.e., significantly more air is supplied than required) are associated with energy waste. In other words, if the forecasted information on the future occupancy of the premises is available, the air volume of the ventilation system may be adjusted in advance so that the premises are ventilated only to the extent necessary to maintain adequate air quality. A similar application can be used in the control of indoor lighting and other energy-using systems.

In summary, V. Motuzienė explained that the consumer and his/her behavior largely determine the energy needs in new and energy-efficient buildings, so it is important to know when he/she is in the building and how he/she tends to behave. Such knowledge enables the application of artificial intelligence in building management, the reduction of energy consumption, and contribution to global decarbonization goals.

TableAir is happy and proud to have contributed to the research conducted by VilniusTech!