Innowatts Outperforms in Load Forecasting Trial

|Sep 30|magazine7 min read

HOUSTON, Sept. 30, 2020 /PRNewswire/ -- Innowatts, a leading energy SaaS platform that utilizes best-in-class artificial intelligence, today announced that it has outperformed five other energy forecasters on most measures in an independent trial

The Electric Power Research Institute (EPRI), an independent, non-profit energy research group, tested nine short-term, building-level energy forecasting models from six vendors against real-world data collected across 12 months, from June 2019 to June 2020. Participants were tasked with generating hour-ahead, six-hour-ahead, day-ahead, and four-day-ahead building-level forecasts, based on hourly and historical load data, as well as site-specific information such as building size and type, location details, and electricity rate plans.

Innowatts' three models outperformed the other six models, as well as a benchmark forecast that assumed energy use would simply hold steady from one hour to the next, with the lowest error across the full range of forecasting scenarios once missing uploads were excluded from error calculations. The forecasts were tested across three metrics (all hours, variable hours, and peak hours) and four horizons (hour ahead, six hours ahead, day ahead, and four days ahead).

During March and April 2020, businesses experienced unprecedented shifts in energy consumption due to nationwide "shelter-in-place" orders. During this period, the trial evaluated the load forecasts of 12 models over six commercial sites, and two of Innowatts' models had the lowest error for all forecast horizons. All three of Innowatts models posted single-digit percentage error rates in all but three of the 24 test conditions, outperforming competitors' models.

"These results provide further evidence of the strength of Innowatts' AI-powered load forecasting models, which are continuously optimized based on usage data from more than 40 million meters from around the world," says Innowatts CEO Siddhartha Sachdeva. "Accurate forecasting is essential for energy providers, and this trial demonstrates that AI-powered, meter-level data intelligence consistently delivers best-in-class predictions regardless of changes in weather or conditions."

About Innowatts:
Innowatts is a leading energy SaaS platform that utilizes best-in-class artificial intelligence to help electricity providers unlock grid edge opportunities, increase customer value, and accelerate the transition to sustainable energy solutions. The Innowatts platform harnesses insights from more than 40 million meters, delivering real-time, customer-centric energy analytics with unprecedented accuracy. With clients and operations across the Americas, Europe, and Asia, Innowatts is a global leader, enabling energy providers to become truly customer-focused and fully leverage the power of data to transform their businesses. For more information, please visit www.innowatts.com.    

Media Contact:
David Wamsley
415-259-9104
[email protected]

Cision View original content:http://www.prnewswire.com/news-releases/innowatts-outperforms-in-load-forecasting-trial-301142428.html

SOURCE Innowatts LLC