Autonomous Building Effort: Making Smart Buildings Smarter

A new research collaboration will focus on super-learners, a foundational machine learning technology that enables autonomy for all building applications.

Move over smart buildings. There is a growing interest in self-contained buildings. Just last week, the Pacific Northwest National Laboratory (PNNL) and PassiveLogic announced their partnership to further develop deep artificial intelligence for predictive building controls. Funded by the US Department of Energy (DOE) to support its mandate to improve the energy efficiency of four million buildings by 2030, the 24-month research collaboration will focus on Superlearners, a fundamental machine learning technology that enables autonomy of all construction applications.

Why the need for such technology? Commercial buildings in the United States consume 13.6 quads of electricity (approximately 35% of the electricity consumed in the United States) and generate 826 million metric tons of carbon dioxide emissions (16% of all carbon dioxide emissions in the United States), according to the US Department of Energy. To put this energy consumption into perspective, consider that the total energy used to transport people and goods from one place to another in the United States represents “only” 28 percent of the total energy consumed.

“The only way to achieve global decarbonization goals is through breakthroughs in building automation and control,” PassiveLogic CEO, Co-Founder and Technology Architect Troy Harvey said in a statement.

Webinar: What's New in IBM MQ: Innovation and Evolution [Register Now]

PNNL’s Autonomous Learning and Reasoning team initiated the PassiveLogic collaboration under a partnership called the Cooperative Research and Development Agreement (CRADA), which has long been a DOE tool to encourage public-private collaborations and advancing technologies to market. The DOE will fund $1 million for PNNL to contribute technology to PassiveLogic.

The agreement will allow PNNL and PassiveLogic to jointly develop and apply their capabilities. The goal is to develop technology that will help building energy systems, such as heating and cooling units and lighting, become fully autonomous, capable of identifying and solving their own operational problems and able to self-optimize their operation.

See also: Autonomous buildings on the horizon?

Autonomous versus intelligent

Buildings, like cars and other smart things, have different levels of intelligence. Take a simple area of ​​interest in a car, such as lane departure safety. Some cars have a basic feature that warns the driver if the car deviates from a lane. Others incorporate self-correcting steering on top of that. Thus, providing a higher level of functionality. And some are adding autonomous driving that would not only keep the car in one lane on a highway, but rely on many other systems to fully navigate a complex path from place to place.

Similarly for buildings, the focus has been on moving from relatively simple smart solutions for temperature control to merging multiple smart systems (e.g. smart elevators, smart lobbies, etc.) that attempt respond to higher-level functions such as optimizing environmental impact. of a building and improve the comfort and safety of its occupants.

Autonomous construction efforts typically start with smart energy management systems. However, some of the ongoing projects, such as Bouygues Construction’s ABC demonstratoralso include water and waste management systems.

Stand-alone building security systems can also be considered. An example would be a system that analyzes video from a network of cameras for multiple purposes. Rather than having a guard watching the monitors, such a system could be used to spot intruders or automatically open a door upon arrival of a known occupant.

Raising the bar on technology

Autonomous buildings will rely on predictive systems that use real-time and historical data about an asset to spot trends that could lead to problems. They will make inferences to help problems in the making. Once detected, an autonomous building would automatically trigger corrective action. This is, in essence, the goal of the PNNL and PassiveLogic partnership, which focuses on developing deep artificial intelligence for predictive building controls.

Another factor to consider is that smart buildings do not exist as isolated entities. They would be part of a smart city that would include interaction between smart water and sanitation systems, traffic management systems, garbage removal and recycling.

An example of work done in this area is the Milan Innovation District (MIND). MIND is a major new district for science, knowledge and innovation on the former Expo site in Milan, Italy. The master plan for the new district includes the development of a hospital, a university and an international research center. The goal of the project is to build sustainable urban facilities that automatically adapt to conditions and use resources efficiently. It is one of many showcase projects for stand-alone buildings emerging around the world.