NCAR develops solar forecasting system for New York State

The National Center for Atmospheric Research (NCAR) has developed an advanced solar energy forecasting system for the state of New York that can predict solar irradiance hours and days in advance.

In an article posted on NCAR’s website, author David Hosansky explained how this system, called NY SolarCast, can help the state achieve its renewable energy goals and save money for ratepayers.

The open-source system draws on weather forecasts, observations of atmosphere conditions, and machine learning techniques to generate its solar forecasts ahead of time. Predictions are issued every 15 minutes and can be used to forecast solar power generation for both major solar farms and rooftop solar panels, Hosansky wrote. And in a one-year testing period, it proved to be highly accurate, consistently coming within about 10 percent of the actual amount of power generated.

The research was funded by the New York Power Authority and the New York State Energy Research and Development Authority. Further, the study was co-managed by the Electric Power Research Institute (EPRI) while the Brookhaven National Lab, the State University of New York at Albany, the New York Independent System Operator (NYISO), and utility Central Hudson served as partners and advisors.

“We’re very pleased that the NY SolarCast system provides accurate forecasting of both utility-scale solar farms and rooftop solar panels,” NCAR scientist Jared Lee, the lead developer, told Hosansky. “Continually improving the accuracy of forecasts is vital for the solar industry, which needs to ensure the reliable delivery of renewable energy and improve the overall performance of the electric grid as more solar energy generation is built.”

As mentioned, more accurate forecasts will help the state meet its goals of 70 percent electrical generation from renewable sources by 2030 and a zero-emission electricity sector by 2040. It will also help save money, as the author explained.

“Successfully forecasting solar irradiance is critical for expanded solar energy production. If an electric utility powers down a coal or natural gas facility in anticipation of energy from the Sun or another renewable source, those plants may not be able to power up fast enough should the amount of sunshine be insufficient. The only option in such a scenario is to buy energy on the spot market, which can be very costly,” Hosansky wrote.

While this was developed for New York, the technology can be applied anywhere.

“This system is applicable worldwide,” Lee said, reported Hosansky. “It is highly configurable and customizable, so it can deliver forecasts at any desired time interval over any forecast region that a utility needs.”