Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting

Yongqian Liu, Yimei Wang, Li Li, Shuang Han, David Infield

Research output: Contribution to journalArticle

12 Citations (Scopus)
83 Downloads (Pure)

Abstract

Numerical weather prediction (NWP) of wind speed (WS) is an important input to wind power forecasting (WPF), which its accuracy will limit the WPF performance. This paper proposes three NWP correcting methods based on the multiple linear regression, a radial basis function neural network, and an Elman neural network. The proposed correction methods exhibit small sample learning and efficient computational ability. So, they are in favour of forecasting the performance of planned large-scale wind farms. To this end, a physical WPF model based on computational fluid dynamics is used to demonstrate the impact of improving the NWP WS data based forecasting. A certain wind farm located in China is selected as the case study, and the measured and NWP WS forecasts before and after correction are taken as inputs to the WPF model. Results show that all three correction methods improve the precision of the NWP WS forecasts, with the nonlinear correction models performing a little better than the linear one. Compared with the original NWP, the three corrected NWP WS have higher annual, single point, and short-term prediction accuracy. As expected, the accuracy of wind power forecasting will increase with the accuracy of the input NWP WS forecast. Moreover, the WS correction enhances the consistency of error variation trends between input WS and output wind power. The proposed WS correction methods greatly improve the accuracy of both original NWP WS and the WPF derived from them.
Original languageEnglish
Article number033302
Number of pages13
JournalJournal of Renewable and Sustainable Energy
Volume8
Issue number3
Early online date20 May 2016
DOIs
Publication statusE-pub ahead of print - 20 May 2016

Fingerprint

Wind power
Computational fluid dynamics
Farms
Neural networks
Linear regression

Keywords

  • wind forecasting
  • numerical weather prediction
  • wind speed
  • wind power forecasting

Cite this

@article{856d08c945cd410c8973e2c25be9d76f,
title = "Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting",
abstract = "Numerical weather prediction (NWP) of wind speed (WS) is an important input to wind power forecasting (WPF), which its accuracy will limit the WPF performance. This paper proposes three NWP correcting methods based on the multiple linear regression, a radial basis function neural network, and an Elman neural network. The proposed correction methods exhibit small sample learning and efficient computational ability. So, they are in favour of forecasting the performance of planned large-scale wind farms. To this end, a physical WPF model based on computational fluid dynamics is used to demonstrate the impact of improving the NWP WS data based forecasting. A certain wind farm located in China is selected as the case study, and the measured and NWP WS forecasts before and after correction are taken as inputs to the WPF model. Results show that all three correction methods improve the precision of the NWP WS forecasts, with the nonlinear correction models performing a little better than the linear one. Compared with the original NWP, the three corrected NWP WS have higher annual, single point, and short-term prediction accuracy. As expected, the accuracy of wind power forecasting will increase with the accuracy of the input NWP WS forecast. Moreover, the WS correction enhances the consistency of error variation trends between input WS and output wind power. The proposed WS correction methods greatly improve the accuracy of both original NWP WS and the WPF derived from them.",
keywords = "wind forecasting, numerical weather prediction, wind speed, wind power forecasting",
author = "Yongqian Liu and Yimei Wang and Li Li and Shuang Han and David Infield",
year = "2016",
month = "5",
day = "20",
doi = "10.1063/1.4950972",
language = "English",
volume = "8",
journal = "Journal of Renewable and Sustainable Energy",
issn = "1941-7012",
number = "3",

}

Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting. / Liu, Yongqian; Wang, Yimei; Li, Li; Han, Shuang; Infield, David.

In: Journal of Renewable and Sustainable Energy, Vol. 8, No. 3, 033302, 20.05.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting

AU - Liu, Yongqian

AU - Wang, Yimei

AU - Li, Li

AU - Han, Shuang

AU - Infield, David

PY - 2016/5/20

Y1 - 2016/5/20

N2 - Numerical weather prediction (NWP) of wind speed (WS) is an important input to wind power forecasting (WPF), which its accuracy will limit the WPF performance. This paper proposes three NWP correcting methods based on the multiple linear regression, a radial basis function neural network, and an Elman neural network. The proposed correction methods exhibit small sample learning and efficient computational ability. So, they are in favour of forecasting the performance of planned large-scale wind farms. To this end, a physical WPF model based on computational fluid dynamics is used to demonstrate the impact of improving the NWP WS data based forecasting. A certain wind farm located in China is selected as the case study, and the measured and NWP WS forecasts before and after correction are taken as inputs to the WPF model. Results show that all three correction methods improve the precision of the NWP WS forecasts, with the nonlinear correction models performing a little better than the linear one. Compared with the original NWP, the three corrected NWP WS have higher annual, single point, and short-term prediction accuracy. As expected, the accuracy of wind power forecasting will increase with the accuracy of the input NWP WS forecast. Moreover, the WS correction enhances the consistency of error variation trends between input WS and output wind power. The proposed WS correction methods greatly improve the accuracy of both original NWP WS and the WPF derived from them.

AB - Numerical weather prediction (NWP) of wind speed (WS) is an important input to wind power forecasting (WPF), which its accuracy will limit the WPF performance. This paper proposes three NWP correcting methods based on the multiple linear regression, a radial basis function neural network, and an Elman neural network. The proposed correction methods exhibit small sample learning and efficient computational ability. So, they are in favour of forecasting the performance of planned large-scale wind farms. To this end, a physical WPF model based on computational fluid dynamics is used to demonstrate the impact of improving the NWP WS data based forecasting. A certain wind farm located in China is selected as the case study, and the measured and NWP WS forecasts before and after correction are taken as inputs to the WPF model. Results show that all three correction methods improve the precision of the NWP WS forecasts, with the nonlinear correction models performing a little better than the linear one. Compared with the original NWP, the three corrected NWP WS have higher annual, single point, and short-term prediction accuracy. As expected, the accuracy of wind power forecasting will increase with the accuracy of the input NWP WS forecast. Moreover, the WS correction enhances the consistency of error variation trends between input WS and output wind power. The proposed WS correction methods greatly improve the accuracy of both original NWP WS and the WPF derived from them.

KW - wind forecasting

KW - numerical weather prediction

KW - wind speed

KW - wind power forecasting

U2 - 10.1063/1.4950972

DO - 10.1063/1.4950972

M3 - Article

VL - 8

JO - Journal of Renewable and Sustainable Energy

JF - Journal of Renewable and Sustainable Energy

SN - 1941-7012

IS - 3

M1 - 033302

ER -