High-quality-tuning forecasting with AI
Farseer and AMART are half of a bigger concerted effort by AES to broaden its investments in renewable power. For instance, the corporate purchased Valcour Wind Power’s six wind farms in New York and in addition builds and operates photo voltaic farms and storage programs in California, Arizona, and several other different US states, in addition to in Brazil and Argentina. These investments come simply as the corporate claims, in its 2023 annual report, that demand from company information facilities within the US is anticipated to roughly double inside the subsequent three years as generative AI deployments broaden.
However with the addition of extra renewable power to its portfolio, climate uncertainty turns into a higher problem for AES. The Farseer machine studying mannequin represents a serious development for the corporate as a result of it analyzes giant quantities of historic climate information to foretell wind farm output with far higher accuracy than up to now, Reyes says.
“As we iterated with Farseer, we’ve been capable of make the mannequin extra correct as a result of the mannequin is trying on the historical past and updates day-after-day,” Reyes factors out. “It proposes next-day technology after which we get the actuals, and the actuals go into the historical past and continues to additional refine what the mannequin is providing you with the following day.”
