One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks

Research output: Contribution to journalArticleResearchpeer review

Authors

View graph of relations

Details

Original languageEnglish
Article number2906
JournalEnergies
Volume11
Issue number11
Early online date25 Oct 2018
Publication statusPublished - Nov 2018

Abstract

We present a method to predict the global horizontal irradiance (GHI) one hour ahead in one-minute resolution using Artificial Neural Networks (ANNs). A feed-forward neural network with Levenberg-Marquardt Backpropagation (LM-BP) was used and was trained with four years of data from all-sky images and measured global irradiance as input. The pictures were recorded by a hemispheric sky imager at the Institute of Meteorology and Climatology (IMuK) of the Leibniz Universität Hannover, Hannover, Germany (52.23 N, 09.42 E, and 50 m above sea level). The time series of the global horizontal irradiance was measured using a thermopile pyranometer at the same site. The new method was validated with a test dataset from the same source. The irradiance is predicted for the first 10-30 min very well; after this time, the length of which is dependent on the weather conditions, the agreement between predicted and observed irradiance is reasonable. Considering the limited range that the camera and the ANN can "see", this is not surprising. When comparing the results to the persistence model, we observed that the forecast accuracy of the new model reduced both the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) of the one-hour prediction by approximately 40% compared to the reference persistence model under various weather conditions, which demonstrates the high capability of the algorithm, especially within the first minutes.

Keywords

    All-sky image, Artificial neural networks, Solar energy, Solar irradiance prediction

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks. / Crisosto, Cristian; Hofmann, Martin; Mubarak, Riyad et al.
In: Energies, Vol. 11, No. 11, 2906, 11.2018.

Research output: Contribution to journalArticleResearchpeer review

Crisosto C, Hofmann M, Mubarak R, Seckmeyer G. One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks. Energies. 2018 Nov;11(11):2906. Epub 2018 Oct 25. doi: 10.3390/en11112906, 10.15488/4836
Crisosto, Cristian ; Hofmann, Martin ; Mubarak, Riyad et al. / One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks. In: Energies. 2018 ; Vol. 11, No. 11.
Download
@article{452708e624ea4049a190775d00e63daa,
title = "One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks",
abstract = "We present a method to predict the global horizontal irradiance (GHI) one hour ahead in one-minute resolution using Artificial Neural Networks (ANNs). A feed-forward neural network with Levenberg-Marquardt Backpropagation (LM-BP) was used and was trained with four years of data from all-sky images and measured global irradiance as input. The pictures were recorded by a hemispheric sky imager at the Institute of Meteorology and Climatology (IMuK) of the Leibniz Universit{\"a}t Hannover, Hannover, Germany (52.23 N, 09.42 E, and 50 m above sea level). The time series of the global horizontal irradiance was measured using a thermopile pyranometer at the same site. The new method was validated with a test dataset from the same source. The irradiance is predicted for the first 10-30 min very well; after this time, the length of which is dependent on the weather conditions, the agreement between predicted and observed irradiance is reasonable. Considering the limited range that the camera and the ANN can {"}see{"}, this is not surprising. When comparing the results to the persistence model, we observed that the forecast accuracy of the new model reduced both the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) of the one-hour prediction by approximately 40% compared to the reference persistence model under various weather conditions, which demonstrates the high capability of the algorithm, especially within the first minutes.",
keywords = "All-sky image, Artificial neural networks, Solar energy, Solar irradiance prediction",
author = "Cristian Crisosto and Martin Hofmann and Riyad Mubarak and Gunther Seckmeyer",
note = "Funding information: This research was funded through a scholarship from the German Academic Exchange Service (DAAD), Germany. The publication of this article was funded by the Open Access Fund of the Leibniz Universit{\"a}t Hannover.",
year = "2018",
month = nov,
doi = "10.3390/en11112906",
language = "English",
volume = "11",
journal = "Energies",
issn = "1996-1073",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "11",

}

Download

TY - JOUR

T1 - One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks

AU - Crisosto, Cristian

AU - Hofmann, Martin

AU - Mubarak, Riyad

AU - Seckmeyer, Gunther

N1 - Funding information: This research was funded through a scholarship from the German Academic Exchange Service (DAAD), Germany. The publication of this article was funded by the Open Access Fund of the Leibniz Universität Hannover.

PY - 2018/11

Y1 - 2018/11

N2 - We present a method to predict the global horizontal irradiance (GHI) one hour ahead in one-minute resolution using Artificial Neural Networks (ANNs). A feed-forward neural network with Levenberg-Marquardt Backpropagation (LM-BP) was used and was trained with four years of data from all-sky images and measured global irradiance as input. The pictures were recorded by a hemispheric sky imager at the Institute of Meteorology and Climatology (IMuK) of the Leibniz Universität Hannover, Hannover, Germany (52.23 N, 09.42 E, and 50 m above sea level). The time series of the global horizontal irradiance was measured using a thermopile pyranometer at the same site. The new method was validated with a test dataset from the same source. The irradiance is predicted for the first 10-30 min very well; after this time, the length of which is dependent on the weather conditions, the agreement between predicted and observed irradiance is reasonable. Considering the limited range that the camera and the ANN can "see", this is not surprising. When comparing the results to the persistence model, we observed that the forecast accuracy of the new model reduced both the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) of the one-hour prediction by approximately 40% compared to the reference persistence model under various weather conditions, which demonstrates the high capability of the algorithm, especially within the first minutes.

AB - We present a method to predict the global horizontal irradiance (GHI) one hour ahead in one-minute resolution using Artificial Neural Networks (ANNs). A feed-forward neural network with Levenberg-Marquardt Backpropagation (LM-BP) was used and was trained with four years of data from all-sky images and measured global irradiance as input. The pictures were recorded by a hemispheric sky imager at the Institute of Meteorology and Climatology (IMuK) of the Leibniz Universität Hannover, Hannover, Germany (52.23 N, 09.42 E, and 50 m above sea level). The time series of the global horizontal irradiance was measured using a thermopile pyranometer at the same site. The new method was validated with a test dataset from the same source. The irradiance is predicted for the first 10-30 min very well; after this time, the length of which is dependent on the weather conditions, the agreement between predicted and observed irradiance is reasonable. Considering the limited range that the camera and the ANN can "see", this is not surprising. When comparing the results to the persistence model, we observed that the forecast accuracy of the new model reduced both the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) of the one-hour prediction by approximately 40% compared to the reference persistence model under various weather conditions, which demonstrates the high capability of the algorithm, especially within the first minutes.

KW - All-sky image

KW - Artificial neural networks

KW - Solar energy

KW - Solar irradiance prediction

UR - http://www.scopus.com/inward/record.url?scp=85057780633&partnerID=8YFLogxK

U2 - 10.3390/en11112906

DO - 10.3390/en11112906

M3 - Article

VL - 11

JO - Energies

JF - Energies

SN - 1996-1073

IS - 11

M1 - 2906

ER -

By the same author(s)