The London borough of Merton identified energy waste valued at £25,000 within 15 minutes of employing a new artificial intelligence tool.
The council turned to AI to make sense of a wealth of energy consumption data in a drive to reduce energy consumption in support of commitments linked to the borough’s climate emergency declaration announced in July.
Using consumption data for council-run schools, algorithms applied by AMR DNA, an Energy Assets service, quickly flagged unnecessary energy use outside normal operating hours. The cost of energy waste was estimated at £25,000.
Now the council is applying the technology across its real estate portfolio, not only to prevent energy waste, but also to leverage continuous data analytics to ensure each building management system ‘learns’ what best energy performance looks like.
“We have been collecting consumption data for many years through automated meter reading, and it has been very useful in identifying the root cause of specific energy-related problems,” said Richard Neil of Merton Council. “We understood the value inherent in the data but analysing the entire portfolio in near real-time would have needed an army of analysts. Now we can accomplish this and more through AMR DNA.”
The building management industry faces the huge challenge of making best use of existing resources, including data. The approach Merton has taken shows it is possible to embrace these challenges to help meet climate change commitments.
George Catto, AMR DNA client services director, commented: “Over half of all London boroughs have now declared a climate change emergency and they, like local authorities all around the country, will likely face challenges around reducing waste energy. AI is set to play a key role in developing the data-driven actions needed to optimise energy consumption in buildings and to help councils move towards carbon neutral operations.”
AMR DNA, which is powered by kWIQly architecture, uses AI-driven processes to interrogate energy data, find patterns of energy waste often hiding in plain sight and then provide tailored recommendations. Thereafter, AI tracks the impact of changes, provides an audit trail of projects, monitors day to day consumption and automatically flags corrective actions that need to be taken. And because analysis is continuous, the best consumption profile for each building is progressively ‘learned’.
