The Baldy Mesa solar + storage project in Southern California is now connected to the grid. The 150 MW solar/75 MW storage project is powered by Amazon, and AES developed and will own the project. Machine learning (ML) models, powered by Amazon Web Services (AWS), help predict when and how the project’s battery unit should charge and return energy to the grid.
“AI is an important tool that is already helping our society transition to carbon-free energy and tackle climate change at scale,” said Kara Hurst, Amazon vice president of Worldwide Sustainability, in a statement press release. “Pairing Amazon-powered solar projects with AI technologies powered by AWS helps ensure the electric grid and the customers it serves receive a steady supply of carbon-free energy for more hours per day, while also helping Amazon to make progress towards our commitment to becoming a more sustainable business.”
To date, Amazon has enabled the development of ten solar projects in combination with battery energy storage systems – representing nearly 1.5 GW of battery energy storage capacity. All ten projects are located in the southwestern US, in California and Arizona, and help power Amazon’s operations, including fulfillment centers, office buildings and Amazon’s data centers, by matching the electricity they use with renewable energy.
At Baldy Mesa, software that uses machine learning, which is built using the AWS service Amazon SageMaker, is expected to analyze up to 33 billion data points annually, according to solutions provider Fluence. The software is designed to get more value out of Baldy Mesa’s battery unit by dynamically optimizing when to buy, store and sell energy based on grid conditions. The same ML solution deployed at a similar location in California could help anticipate last year’s statewide heat wave and helped stabilize the electrical grid by providing stored solar energy when it was needed most.
News item from Amazon