Machine learning found farm age, cloud cover impact performance during a storm
Sandia National Laboratories researchers combined large sets of real-world solar data and advanced machine learning to study the impacts of severe weather on U.S. solar farms, and sort out what factors affect energy generation. Their results were published earlier this month in the scientific journal Applied Energy.
Hurricanes, blizzards, hailstorms and wildfires all pose risks to solar farms both directly in the form of costly damage and indirectly in the form of blocked sunlight and reduced electricity output. Two Sandia researchers scoured maintenance tickets from more than 800 solar farms in 24 states and combined that information with electricity generation data and weather records to assess the effects of severe weather on the facilities. By identifying the factors that contribute to low performance, they hope to increase the resiliency of solar farms to extreme weather.
“Trying to understand how future climate conditions could impact our national energy infrastructure, is exactly what we need to be doing if we want our renewable energy sector to be resilient under a changing climate,” said Thushara Gunda, the senior researcher on the project. “Right now, we’re focused on extreme weather events, but eventually we’ll extend into chronic exposure events like consistent extreme heat.”
Hurricanes and snow and storms, oh my!
The Sandia research team first used natural-language processing, a type of machine learning used by smart assistants, to analyze six years of solar maintenance records for key weather-related words. The analysis methods they used for this study has since been published and is freely available for other photovoltaic researchers and operators.
“Our first step was to look at the maintenance records to decide which weather events we should even look at,” said Gunda. “The photovoltaic community talks about hail a lot, but the data in the maintenance records tell a different story.”
While hailstorms tend to be very costly, they did not appear in solar farm maintenance records, likely because operators tend to document hail damage in the form of insurance claims, Gunda said. Instead, she found that hurricanes were mentioned in almost 15% of weather-related maintenance records, followed by the other weather terms, such as snow, storm, lightning and wind.
“Some hurricanes damage racking — the structure that holds up the panels — due to the high winds,” said Nicole Jackson, the lead author on the paper. “The other major issue we’ve seen from the maintenance records and talking with our industry partners is flooding blocking access to the site, which delays the process of turning the plant back on.”
Read about how researchers are using machine learning to find the most important factors and more in the complete news release.
Keywords:
August 31, 2021