An adaptive multi-modeling approach to solar nowcasting

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

The ability to forecast solar irradiance in near-real time (nowcasting) is crucial in managing the integration of solar energy in power grids. This paper focuses on minute-by-minute forecasts of the normalized clearness index, a measure of global horizontal irradiation, within a fifteen steps-ahead temporal horizon, using data collected with a radiometric station in Doha, Qatar, for the period January-December 2014. We describe a novel multi-modeling approach to solar forecasting that uses supervised classification of forecasting evaluation results from diverse stochastic models to select the best predictions, according to their expected superiority in terms of lower error rate. The hypothesis that such a multi-modeling approach rivals the performance of any single forecasting model is tested with reference to two autoregressive models, of order 3 and 11 respectively, a support vector regression model, and a persistence model which provide the baseline for solar prediction. The advantages of the proposed approach are demonstrated in an experimental evaluation where its application with these four models shows a relative skill score improvement of 44.92% over the baseline model, and 19.06% over the best performing model (autoregressive of order 11).

Original languageEnglish
Pages (from-to)77-85
Number of pages9
JournalSolar Energy
Volume125
DOIs
Publication statusPublished - 1 Feb 2016

Fingerprint

Stochastic models
Solar energy
Irradiation

Keywords

  • Autoregressive modeling
  • Normalized clearness index
  • Solar radiation forecasting
  • Support vector regression

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Materials Science(all)

Cite this

An adaptive multi-modeling approach to solar nowcasting. / Sanfilippo, Antonio; Martin-Pomares, Luis; Mohands, Nassma; Astudillo, Daniel; Bachour, Dunia.

In: Solar Energy, Vol. 125, 01.02.2016, p. 77-85.

Research output: Contribution to journalArticle

@article{38bcd0b932a744ffb0a769d8ecfa8362,
title = "An adaptive multi-modeling approach to solar nowcasting",
abstract = "The ability to forecast solar irradiance in near-real time (nowcasting) is crucial in managing the integration of solar energy in power grids. This paper focuses on minute-by-minute forecasts of the normalized clearness index, a measure of global horizontal irradiation, within a fifteen steps-ahead temporal horizon, using data collected with a radiometric station in Doha, Qatar, for the period January-December 2014. We describe a novel multi-modeling approach to solar forecasting that uses supervised classification of forecasting evaluation results from diverse stochastic models to select the best predictions, according to their expected superiority in terms of lower error rate. The hypothesis that such a multi-modeling approach rivals the performance of any single forecasting model is tested with reference to two autoregressive models, of order 3 and 11 respectively, a support vector regression model, and a persistence model which provide the baseline for solar prediction. The advantages of the proposed approach are demonstrated in an experimental evaluation where its application with these four models shows a relative skill score improvement of 44.92{\%} over the baseline model, and 19.06{\%} over the best performing model (autoregressive of order 11).",
keywords = "Autoregressive modeling, Normalized clearness index, Solar radiation forecasting, Support vector regression",
author = "Antonio Sanfilippo and Luis Martin-Pomares and Nassma Mohands and Daniel Astudillo and Dunia Bachour",
year = "2016",
month = "2",
day = "1",
doi = "10.1016/j.solener.2015.11.041",
language = "English",
volume = "125",
pages = "77--85",
journal = "Solar Energy",
issn = "0038-092X",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - An adaptive multi-modeling approach to solar nowcasting

AU - Sanfilippo, Antonio

AU - Martin-Pomares, Luis

AU - Mohands, Nassma

AU - Astudillo, Daniel

AU - Bachour, Dunia

PY - 2016/2/1

Y1 - 2016/2/1

N2 - The ability to forecast solar irradiance in near-real time (nowcasting) is crucial in managing the integration of solar energy in power grids. This paper focuses on minute-by-minute forecasts of the normalized clearness index, a measure of global horizontal irradiation, within a fifteen steps-ahead temporal horizon, using data collected with a radiometric station in Doha, Qatar, for the period January-December 2014. We describe a novel multi-modeling approach to solar forecasting that uses supervised classification of forecasting evaluation results from diverse stochastic models to select the best predictions, according to their expected superiority in terms of lower error rate. The hypothesis that such a multi-modeling approach rivals the performance of any single forecasting model is tested with reference to two autoregressive models, of order 3 and 11 respectively, a support vector regression model, and a persistence model which provide the baseline for solar prediction. The advantages of the proposed approach are demonstrated in an experimental evaluation where its application with these four models shows a relative skill score improvement of 44.92% over the baseline model, and 19.06% over the best performing model (autoregressive of order 11).

AB - The ability to forecast solar irradiance in near-real time (nowcasting) is crucial in managing the integration of solar energy in power grids. This paper focuses on minute-by-minute forecasts of the normalized clearness index, a measure of global horizontal irradiation, within a fifteen steps-ahead temporal horizon, using data collected with a radiometric station in Doha, Qatar, for the period January-December 2014. We describe a novel multi-modeling approach to solar forecasting that uses supervised classification of forecasting evaluation results from diverse stochastic models to select the best predictions, according to their expected superiority in terms of lower error rate. The hypothesis that such a multi-modeling approach rivals the performance of any single forecasting model is tested with reference to two autoregressive models, of order 3 and 11 respectively, a support vector regression model, and a persistence model which provide the baseline for solar prediction. The advantages of the proposed approach are demonstrated in an experimental evaluation where its application with these four models shows a relative skill score improvement of 44.92% over the baseline model, and 19.06% over the best performing model (autoregressive of order 11).

KW - Autoregressive modeling

KW - Normalized clearness index

KW - Solar radiation forecasting

KW - Support vector regression

UR - http://www.scopus.com/inward/record.url?scp=84951819800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951819800&partnerID=8YFLogxK

U2 - 10.1016/j.solener.2015.11.041

DO - 10.1016/j.solener.2015.11.041

M3 - Article

VL - 125

SP - 77

EP - 85

JO - Solar Energy

JF - Solar Energy

SN - 0038-092X

ER -