We use cookies to to enhance the service we deliver you. By using this site, you agree to our use of cookies as described in our Cookie Policy.

Skip to main content
News Regulation

National Grid in talks to use AI to help manage supply and demand

Image description required

National Grid is reportedly in talks with Google’s machine-learning company DeepMind to see how the British firm’s artificial intelligence (AI) technology can be used to help manage supply and demand and across the energy system.

Speaking to the Financial Times (£), DeepMind chief executive Demis Hassabis said the company was in the “early stages” of discussions with the system operator to determine the role AI could have in managed the grid.

“It would be amazing if you could save 10% of the country’s energy usage without any new infrastructure, just from optimisation. That’s pretty exciting ,” he told the FT.

DeepMind added that there is particular interest in helping to better integrate renewable energy onto the grid by using machine learning to predict peaks in demand and supply, adding that it was in the process of exploring a “possible partnership”.

A statement from National Grid confirmed the talks were underway and said: “We are always excited to look at how the latest advances in technology can bring improvements in our performance, ensure we are making the best use of renewable energy, and help save money for bill payers.”

Since being bought by Google in 2014, three years after being founded by Hassabis, machine learning researcher Shane Legg and British entrepreneur Mustafa Suleyman, DeepMind has shown successful applications in reducing energy usage.

Last July the company announced it had cut electricity usage at Google’s data centres by 15%, while the machine learning algorithms had been used to predict load on the data centres’ cooling systems and control equipment, leading to a 40% fall in the amount of energy used for cooling.

DeepMind has said this would be considered a huge improvement in any large scale energy consuming environment and is now looking to do the same for grid-scale applications.

“We think there’s no reason why you can't think of a whole national grid of a country in the same way as you can the data centres,” Hassabis stated.

Speaking at a conference in November last year, Suleyman said: “What we’re ultimately motivated by is taking these techniques and applying them to solve intractable real-world problems.

"All of our algorithms we develop are inherently general so given some dataset we should be able to train an algorithm, based on some inputs, develop a model, predict some outputs. Provided we have access to the controls, we should be able to deliver similar sorts of performance, so we're very excited about the potential here."

AI is rapidly being adopted across the energy space for a number of applications, such as Upside Energy’s Virtual Energy Store which is being used to manage a portfolio of storage assets and provide real-time energy reserves to the grid.

Open Energi has also been exploring how AI and machine learning techniques can be used to manage large amounts of demand-side flexibility in service of a smart grid system.

Writing for Clean Energy News last month, ‎technical director Michael Bironneau argued that machine learning could be used to help unlock up to 6GWs of demand-side flexibility which can be shifted during the evening peak without affecting end users.

“AI can help us to unlock this demand-side flexibility and build an electricity system fit for the future; one which cuts consumer bills, integrates renewable energy efficiently, and secures our energy supplies for generations to come,” he said.


End of content

No more pages to load