| Work Detail |
Baldy Mesa, a solar farm enabled by Amazon and operated by AES, uses Amazon Web Services’ machine learning models to predict when and how the project’s battery unit should charge and discharge energy back to the grid.
The project aims to tackle the challenge of generating and storing a sustainable flow of solar power after the sun goes down.
“AI is an important tool that’s already helping our society make the transition to carbon-free energy and address climate change at scale,” said Kara Hurst, Amazon’s VP of Worldwide Sustainability.
“Pairing solar projects enabled by Amazon with AI technologies powered by AWS helps to ensure the grid and the customers it serves receive a steady supply of carbon-free energy for more hours each day, while also helping Amazon make progress toward our commitment to be a more sustainable company.”
The company has established over 500 solar and wind projects internationally, resulting in Amazon’s portfolio having the potential to power 7.2m homes in the US per annum.
To date, Amazon has enabled the development of 10 solar energy projects paired with battery energy storage systems. These represent nearly 1.5 gigawatts (GW) of battery energy storage capacity and are based in California and Arizona.
Baldy Mesa is one of these projects along with Bellefield, the US’ largest planned solar-plus-storage project. Amazon’s debut rooftop solar array and battery storage unit was installed at Amazon’s San Bernadino Air Hub.
By matching their used electricity with renewable energy, the projects power Amazon operations including fulfilment centres, offices, and data centres.
Machine learning on the rise
Machine learning is a tool equipped by carbon-free energy owners and operators with increasing frequency to reinforce energy production and stabilise the grid. Operators can benefit from such technology through real-time weather data and historical grid data.
Up to 33bn data points are expected to be analysed by Baldy Mesa’s machine learning software, according to solutions provider Fluence.
More value will be extracted from Baldy Mesa’s battery unit by looking at the grid conditions and optimising when to buy, store and sell energy.
A similar site in California also utilised the same ML solution to predict 2023’s state-wide heatwave and store solar energy at the most convenient point. Such uses of ML are expected to help operators to adapt to increased temperatures due to climate change while relieving strain on the power grid caused by increased use of air units.
“Battery storage projects enable increased use of renewable energy, helping ensure that the clean energy from solar and wind projects is available to the grid at all times,” said Kevin Hagen, the Clean Energy Buyers Association’s interim CEO.
“Energy storage, smarter and more interactive load management tools and AI are among the new technologies that hold significant potential in a lower-cost transition to carbon-free energy.” |
