De-Risking Large-Scale PV Systems Through Data Analytics

Research output: NRELPresentation


Large-scale photovoltaic system performance analysis is being conducted within the US Department of Energy's-sponsored PV Fleet Performance Data Initiative. This collaboration with commercial PV system owners collects and evaluates PV field performance data, and provides reports on aggregated results. Drawing on over 2200 sites across the US and over 24,000 separate PV inverters we have collected in excess of 8.3 gigawatts (GW) of performance data, representing 6-7% of the entire US installed PV capacity. A mixture of utility-scale and large commercial systems are represented, averaging 4.1 megawatts (MW) in size and 5 years in age. Initial results show average system degradation rates at -0.75% / year, which is slightly higher than historically reported module-level values of -0.5%/year. We also found that the availability of systems averaged 97.7%, which is lower than the typical 99% uptime assumed by many project economic forecasts. Given these results, we compared monthly performance with expected production values, based on satellite weather data and a simple PVWatts performance model. We found that systems were performing within 10% of monthly expectation over 90% of the time, with a fleet average vs expected monthly value of 0.994. We also evaluated the impact of extreme weather events on system performance, and found a range of short-term and longer-term performance effects ranging from grid outage, system downtime, module damage and accelerated long-term degradation rate.
Original languageAmerican English
Number of pages22
StatePublished - 2023

Publication series

NamePresented at the RE Plus Renewing What's Possible Event, 11-14 September 2023, Las Vegas, Nevada

NREL Publication Number

  • NREL/PR-5K00-87455


  • analysis
  • commercial
  • degradation rate
  • performance
  • PV system


Dive into the research topics of 'De-Risking Large-Scale PV Systems Through Data Analytics'. Together they form a unique fingerprint.

Cite this