United Kingdom-based grid operator National Grid is discussing the use of artificial intelligence (AI) to improve grid operations, according to Clean Energy News.
National Grid says it is in early stage discussions with DeepMind, a U.K. AI company that is now a unit of Alphabet, the parent company of Google.
- The two companies are reportedly exploring how machine learning can be used to predict peaks in demand and supply in order to maximize the integration of renewable energy resources.
The benefits of renewable energy resources do not come without challenges. California has its duck curve problem, which occurs when the supply of solar power falls off sharply in the evening just as demand is rising
A recent report by the U.K. Energy Research Centre found that while renewables were becoming more competitive with fossil generation, more flexibility would have to be built into the system in order to avoid spiraling costs.
Concerned about a volatile supply-demand balance, National Grid created a supplemental balancing reserve in the winter of 2014. But the roughly $220 million program was never used.
DeepMind says its algorithms can help "help energy systems reduce their environmental impact," according to Financial Times. One possibility is "using machine learning to predict peaks in demand and supply," helping National Grid maximize the use of renewable energy.
According to the AI company, its algorithms helped the company's data centers reduce the amount of energy consumed for cooling it by 40%.
"Every improvement in data centre efficiency reduces total emissions into our environment and with technology like DeepMind’s, we can use machine learning to consume less energy and help address one of the biggest challenges of all—climate change," DeepMind said in a blog post.