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

Research output: Contribution to conferencePaper


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 10-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 pages8
StatePublished - 2022
Event2022 IEEE Power & Energy Society General Meeting - Denver, Colorado
Duration: 17 Jul 202221 Jul 2022


Conference2022 IEEE Power & Energy Society General Meeting
CityDenver, Colorado

Bibliographical note

See NREL/CP-5D00-84957 for paper as published in proceedings

NREL Publication Number

  • NREL/CP-5D00-83163


  • 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: Preprint'. Together they form a unique fingerprint.

Cite this