Preprints
https://doi.org/10.5194/amt-2023-26
https://doi.org/10.5194/amt-2023-26
13 Feb 2023
 | 13 Feb 2023
Status: this preprint is currently under review for the journal AMT.

Validation of a camera-based intra-hour irradiance nowcasting model using synthetic cloud data

Philipp Gregor, Tobias Zinner, Fabian Jakub, and Bernhard Mayer

Abstract. This work introduces the novel short-term nowcasting model MACIN, which predicts direct normal irradiance (DNI) for solar energy applications based on hemispheric sky images from two all-sky imagers (ASI). With a synthetic setup based on simulated cloud scenes, the model and its components were validated in depth. We trained a convolutional neural network to identify clouds in ASI images and derive their height and motion using sparse matching. In contrast to other studies, all derived cloud information from both ASIs and multiple timesteps are combined into an optimal model state using techniques from data assimilation. This state is advected to predict future cloud positions and compute DNI for lead times up to 20 minutes. For the cloudmasks derived from the ASI images we found a pixel accuracy of 94.66 % compared to the references available in the synthetic setup. The relative error of derived cloud base heights is 4 % and cloud motion error is in the range of 0.1 ms−1. For the DNI nowcasts, we found an improvement over persistence for lead times larger than one minute. Using the synthetic setup, we computed a DNI reference for a point and also an area of 500m × 500 m. Errors for area nowcasts as required, e.g., for photovoltaics plants, are smaller compared to errors for point nowcasts. Overall, the novel ASI nowcasting model and its components proved to work within the synthetic setup.

Philipp Gregor et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2023-26', Anonymous Referee #1, 13 Mar 2023
  • RC2: 'Comment on amt-2023-26', Anonymous Referee #2, 14 Mar 2023

Philipp Gregor et al.

Philipp Gregor et al.

Viewed

Total article views: 265 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
207 49 9 265 6 3
  • HTML: 207
  • PDF: 49
  • XML: 9
  • Total: 265
  • BibTeX: 6
  • EndNote: 3
Views and downloads (calculated since 13 Feb 2023)
Cumulative views and downloads (calculated since 13 Feb 2023)

Viewed (geographical distribution)

Total article views: 273 (including HTML, PDF, and XML) Thereof 273 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 24 Mar 2023
Download
Short summary
This work introduces MACIN, a model for short-term forecasting of direct irradiance for solar energy applications. MACIN exploits cloud images of multiple cameras to predict irradiances. The model is applied to artificial images of clouds from a weather model. The artificial cloud data allows for a more in-depth evaluation and attribution of errors compared to real data. Good performance of derived cloud information and significant forecast improvements over a baseline forecast were found.