Combining Deep Learning and Physical Models: A Benchmark Study on All‐Sky Imager‐Based Solar Nowcasting Systems

Solar RRL, vol. 8

Abstract

Intermittent solar irradiance due to passing clouds poses challenges for integrating solar energy into existing infrastructure. By making use of intrahour nowcasts (very short‐term forecasts), changing conditions of solar irradiance can be anticipated. All‐sky imagers, capturing sky conditions at high spatial and temporal resolution, can be the basis of such nowcasting systems. Herein, a deep learning (DL) model for solar irradiance nowcasts based on the transformer architecture is presented. The model is trained end‐to‐end using sequences of sky images and irradiance measurements as input to generate point‐forecasts up to 20 min ahead. Further, the effect of integrating this model into a hybrid system, consisting of a physics‐based model and smart persistence, is examined. A comparison between the DL and two hybrid models (with and without the DL model) is conducted on a benchmark dataset. Forecast accuracy for deterministic point‐forecasts is analyzed under different conditions using standard error metrics like root‐mean‐square error and forecast skill. Furthermore, spatial and temporal aggregation effects are investigated. In addition, probabilistic nowcasts for each model are computed via a quantile approach. Overall, the DL model outperforms both hybrid models under the majority of conditions and aggregation effects.

Authors 10

1. Yann Fabel corresponding

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   German Aerospace Center (DLR) Institute for Solar Research Calle Doctor Carracido No 42, floor 1 04005 Almería Spain

2. Bijan Nouri

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   German Aerospace Center (DLR) Institute for Solar Research Calle Doctor Carracido No 42, floor 1 04005 Almería Spain

3. Stefan Wilbert

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   German Aerospace Center (DLR) Institute for Solar Research Calle Doctor Carracido No 42, floor 1 04005 Almería Spain

4. Niklas Benedikt Blum

   Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

   Affiliation as printed

   German Aerospace Center (DLR) Institute for Solar Research Calle Doctor Carracido No 42, floor 1 04005 Almería Spain

5. Dominik Schnaus

   Technical University of Munich

   Affiliation as printed

   Chair of Computer Vision & Artificial Intelligence Technical University Munich 85748 Garching Germany

6. Rudolph Triebel

   Technical University of Munich

   Affiliation as printed

   Chair of Computer Vision & Artificial Intelligence Technical University Munich 85748 Garching Germany

7. Luis Fernando Zarzalejo

   Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas

   Affiliation as printed

   CIEMAT Energy Department Renewable Energy Division 28040 Madrid Spain

8. Enrique Ugedo

   Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas

   Affiliation as printed

   CIEMAT Energy Department Renewable Energy Division 28040 Madrid Spain

9. Julia Kowalski Aachen Chair of Methods for Model‐based Development in Computational Engineering

   RWTH Aachen University

   Affiliation as printed

   Chair of Methods for Model‐based Development in Computational Engineering RWTH Aachen University 52056 Aachen Germany

10. Robert Pitz‐Paal Aachen Chair of Solar Technology

    Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) · RWTH Aachen University

    Affiliation as printed

    Chair of Solar Technology RWTH Aachen University 52056 Aachen Germany

    German Aerospace Center (DLR) Institute for Solar Research 51147 Cologne Germany