A new research project from the University of Wollongong’s SMART Infrastructure Facility is exploring ways to improve energy efficiency in shopping centres and retail outlets through artificial intelligence and machine learning.

The project is being conducted in partnership with building services providers, Grosvenor Engineering Group and Enviro Building Services, and the NSW Government, and is part of the university’s SMART’s Digital Living Lab, which provides solutions for smarter living in buildings using the Internet of Things.

The project aims to solve three key practical problems in building management: accurate counting of building and room occupation, accurate forecasting of indoor temperature to help determine the mode of operations for HVAC systems and the detection of issues in rotating equipment, such as fans, before they become problems.

Using anonymised real building data from Grosvenor and image data from Enviro, the researchers will train deep neural networks to predict outcomes and optimise the heating, ventilation and cooling of shopping centres and retail outlets.

While accurate estimates of building occupancy are necessary to optimise both HVAC systems and space utlisation in shopping centres and retail outlets, current systems used for this purpose are only about 66 per cent accurate. The image-recognition based system that the researchers are using is about 93 per cent accurate.

“The project’s focus is to increase the efficiency of building environments,” Dr Rohan Wickramasuriya, senior research fellow on the project, said.

“For instance, by forecasting room temperatures as a function of external and internal conditions, we expect to find that it is more efficient to pump cool night air into a building, rather than turning off the system at 6pm and allowing rooms to heat up due to lack of ventilation,”

The results of the project are expected to be delivered mid-year.