SMART researchers are about to complete a project that has the potential to revolutionise the efficiency of keeping building temperatures consistently within the comfort zone.

Senior research fellow Dr Rohan Wickramasuriya is leading a team that is looking at ways of optimising the heating, ventilation and cooling of buildings under the Building Energy Monitoring project.

“One of the usual ways of doing this is to start your cooling at 6am and run it until 6pm on a constant flow,” Dr Wickramasuriya said.

“There are several obvious problems with this.

“The first is that not many people get in at 6am, the second is that it takes no account of whether the room is occupied, or how many people in the room.

“The regimes of cooling and heating flows are usually set by an engineer when the building is commissioned and then set in stone.”

Funded by Grosvenor Engineering Group, Enviro Building Services and the NSW Government (through the Department of Industry), the project is part of SMART’s Digital Living Lab, which is providing an Internet of Things Network to create smarter living.

The project has four aims.

The first is to detect occupation of rooms throughout the day by using cameras that take frequent images, which are then fed through an algorithm that recognizes people in those images and records them.

Privacy concerns are addressed by the fact that the images are processed by the inbuilt algorithm and never sent to an outside server. That server will only receive the occupation data.

This video-based analytics system has an accuracy of 92 per cent – well ahead of the 80 per cent target – and more than 30 per cent more accurate that the laser systems that are currently used;

The second aim is to use this data and combine it with measurements of the historical temperature of a room, the outside temperature, solar radiation and the cooling/heating power deliver by the HVAC system to forecast room temperatures. The long short-term memory-based deep neural network algorithms developed in this research is capable of forecasting room temperatures at a much higher accuracy, compared to traditional time series forecasting algorithms.

The third aim is to develop a vibration sensor prototype that will record initial deviations from the standard for any moving part – a fan motor for example. This will alert building managers to equipment malfunction, long before it becomes a crisis.

And the fourth aim is to develop a web interface for the data that is easily accessible by the end user.

“The aim of this project is to increase the efficiency of building environments,” Dr Wickramasuriya said.

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

The project is due to be completed this year.