Occlusion-Perturbed Deep Learning for Probabilistic Solar Forecasting via Sky Images

Research output: Contribution to conferencePaperpeer-review

3 Scopus Citations


Solar forecasting is shifting to the probabilistic paradigm due to the inherent uncertainty within the solar resource. Input uncertainty quantification is one of the widely-used and best-performing ways to model solar uncertainty. However, compared to other sources of inputs, such as numerical weather prediction models, pure sky image-based probabilistic solar forecasting lags behind. In this research, an occlusion-perturbed convolutional neural network, named the PSolarNet, is developed. The PSolarNet provides very short-term deterministic forecasts, forecast scenarios, and probabilistic forecasts of the global horizontal irradiance from sky image sequences. Case studies based on 6 years of open-source data show that the developed PSolarNet is able to generate accurate to-minute ahead deterministic forecasts with a 5.62% normalized root mean square error, realistic and diverse forecast scenarios with a 0.966 average correlation with the actual time series, and reliable and sharp probabilistic forecasts with a 2.77% normalized continuous ranked probability score.

Original languageAmerican English
Number of pages5
StatePublished - 2022
Event2022 IEEE Power and Energy Society General Meeting, PESGM 2022 - Denver, United States
Duration: 17 Jul 202221 Jul 2022


Conference2022 IEEE Power and Energy Society General Meeting, PESGM 2022
Country/TerritoryUnited States

Bibliographical note

See NREL/CP-5D00-83163 for preprint

NREL Publication Number

  • NREL/CP-5D00-84957


  • Bayesian model averaging
  • Deep learning
  • sky image processing
  • solar forecasting


Dive into the research topics of 'Occlusion-Perturbed Deep Learning for Probabilistic Solar Forecasting via Sky Images'. Together they form a unique fingerprint.

Cite this