How Artificial Intelligence Is Improving the Energy Efficiency of Buildings.

A lot of energy is consumed by buildings. In fact, the Alliance to Save Energy, a nonprofit energy efficiency advocacy group, says buildings account for about 40% of all U.S. energy consumption and a similar proportion of greenhouse gas emissions. Some estimates suggest about 45% of the energy used in commercial buildings is consumed by heating, ventilation, and air conditioning (HVAC) systems, of which, as much as 30% is often wasted.

Most power companies these days have energy efficiency programs that help customers identify waste and implement energy-saving measures, but there are also non-utility providers working on solutions. Montreal, Canada–based BrainBox AI is one of them. It’s using artificial intelligence (AI) to significantly reduce energy consumption in buildings.

“We’ve developed an autonomous artificial intelligence technology that applies to commercial buildings in order to render their heating and cooling needs, which is typically the single largest consumer of energy in a building, and to make those much more efficient and certainly much more flexible to outside demands and occupant demands,” Sam Ramadori, president of BrainBox AI, said as a guest on The POWER Podcast.

The company’s autonomous AI HVAC technology studies how a building operates and analyses the external factors affecting it. It identifies potential improvement opportunities and then acts to optimize the building’s system. It requires no human intervention and reacts to changes in the built environment immediately to maintain the highest tenant comfort and energy efficiency at all times.

“What’s exciting is you don’t have to picture a room full of dozens of engineers managing and monitoring these buildings. It’s truly the AI optimizing the building in real time without human intervention,” Ramadori said.

Surprisingly, the BrainBox technology does not require any changes to be made to most buildings’ HVAC systems. It simply connects to what’s already installed and utilizes existing sensors and data, along with third-party resources such as weather forecasts and occupancy information, to drive decision-making.

It’s easy to imagine how a building’s HVAC needs change through the course of a day. For example, east-facing offices may require more cooling in earlier parts of the day as the sun rises, while west-facing offices may require more cooling later in the day as the sun shines through windows in the afternoon. The BrainBox technology accounts for those sorts of changes and adjusts dampers to keep each zone optimally heated or cooled. But it doesn’t end there, the AI is constantly learning and evolving.

Ramadori explained how changes in a building’s surroundings would also be picked up and accounted for by the technology. “What happens if across the street on the south-facing side, right now there’s a parking lot, and then in a year, they build up a tower right next to it? Well, what happens, that tower is now throwing shade onto part of your building for a part of the day. So suddenly, the behavior of those rooms has changed,” Ramadori said. “What’s exciting is no one has to tell the AI that there’s a building that just went up next door, it will just learn that ‘Wait a second, those rooms that used to get hot at noon, you know, for the bottom half of my building, no longer are getting that hot anymore.’ It doesn’t know why, but it doesn't matter. It just knows. It’ll relearn—by itself without a human reprogramming it—it’ll relearn the new behavior caused by that building built next door.”

“We’re cutting energy consumption in a building typically by 20 to 25%—so, it’s a large reduction—and we do so without turning one screw, which makes it super exciting and powerful,” said Ramadori.