Short-term wind power forecasting based on clustering pre-calculated CFD method

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

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

To meet the increasing wind power forecasting (WPF) demands of newly built wind farms without historical data, physical WPF methods are widely used. The computational fluid dynamics (CFD) pre-calculated flow fields (CPFF)-based WPF is a promising physical approach, which can balance well the competing demands of computational efficiency and accuracy. To enhance its adaptability for wind farms in complex terrain, a WPF method combining wind turbine clustering with CPFF is first proposed where the wind turbines in the wind farm are clustered and a forecasting is undertaken for each cluster. K-means, hierarchical agglomerative and spectral analysis methods are used to establish the wind turbine clustering models. The Silhouette Coefficient, Calinski-Harabaz index and within-between index are proposed as criteria to evaluate the effectiveness of the established clustering models. Based on different clustering methods and schemes, various clustering databases are built for clustering pre-calculated CFD (CPCC)-based short-term WPF. For the wind farm case studied, clustering evaluation criteria show that hierarchical agglomerative clustering has reasonable results, spectral clustering is better and K-means gives the best performance. The WPF results produced by different clustering databases also prove the effectiveness of the three evaluation criteria in turn. The newly developed CPCC model has a much higher WPF accuracy than the CPFF model without using clustering techniques, both on temporal and spatial scales. The research provides supports for both the development and improvement of short-term physical WPF systems.
LanguageEnglish
Article number854
Number of pages19
JournalEnergies
Volume11
Issue number4
DOIs
Publication statusPublished - 5 Apr 2018

Fingerprint

Wind Power
Computational Fluid Dynamics
Wind power
Forecasting
Computational fluid dynamics
Clustering
Farms
Wind Turbine
Wind turbines
Flow Field
Flow fields
K-means
Demand Forecasting
Spectral Clustering
Silhouette
Historical Data
Hierarchical Clustering
Evaluation
Computational efficiency
Adaptability

Keywords

  • wind turbine
  • clustering model
  • computational fluid dynamics
  • pre-calculated database
  • wind power forecasting

Cite this

Wang, Yimei ; Liu, Yongqian ; Li, Li ; Infield, David ; Han, Shuang. / Short-term wind power forecasting based on clustering pre-calculated CFD method. In: Energies. 2018 ; Vol. 11, No. 4.
@article{f489d9e207f84a3a928e8a6007a00efe,
title = "Short-term wind power forecasting based on clustering pre-calculated CFD method",
abstract = "To meet the increasing wind power forecasting (WPF) demands of newly built wind farms without historical data, physical WPF methods are widely used. The computational fluid dynamics (CFD) pre-calculated flow fields (CPFF)-based WPF is a promising physical approach, which can balance well the competing demands of computational efficiency and accuracy. To enhance its adaptability for wind farms in complex terrain, a WPF method combining wind turbine clustering with CPFF is first proposed where the wind turbines in the wind farm are clustered and a forecasting is undertaken for each cluster. K-means, hierarchical agglomerative and spectral analysis methods are used to establish the wind turbine clustering models. The Silhouette Coefficient, Calinski-Harabaz index and within-between index are proposed as criteria to evaluate the effectiveness of the established clustering models. Based on different clustering methods and schemes, various clustering databases are built for clustering pre-calculated CFD (CPCC)-based short-term WPF. For the wind farm case studied, clustering evaluation criteria show that hierarchical agglomerative clustering has reasonable results, spectral clustering is better and K-means gives the best performance. The WPF results produced by different clustering databases also prove the effectiveness of the three evaluation criteria in turn. The newly developed CPCC model has a much higher WPF accuracy than the CPFF model without using clustering techniques, both on temporal and spatial scales. The research provides supports for both the development and improvement of short-term physical WPF systems.",
keywords = "wind turbine, clustering model, computational fluid dynamics, pre-calculated database, wind power forecasting",
author = "Yimei Wang and Yongqian Liu and Li Li and David Infield and Shuang Han",
year = "2018",
month = "4",
day = "5",
doi = "10.3390/en11040854",
language = "English",
volume = "11",
journal = "Energies",
issn = "1996-1073",
number = "4",

}

Short-term wind power forecasting based on clustering pre-calculated CFD method. / Wang, Yimei; Liu, Yongqian; Li, Li; Infield, David; Han, Shuang.

In: Energies, Vol. 11, No. 4, 854, 05.04.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Short-term wind power forecasting based on clustering pre-calculated CFD method

AU - Wang, Yimei

AU - Liu, Yongqian

AU - Li, Li

AU - Infield, David

AU - Han, Shuang

PY - 2018/4/5

Y1 - 2018/4/5

N2 - To meet the increasing wind power forecasting (WPF) demands of newly built wind farms without historical data, physical WPF methods are widely used. The computational fluid dynamics (CFD) pre-calculated flow fields (CPFF)-based WPF is a promising physical approach, which can balance well the competing demands of computational efficiency and accuracy. To enhance its adaptability for wind farms in complex terrain, a WPF method combining wind turbine clustering with CPFF is first proposed where the wind turbines in the wind farm are clustered and a forecasting is undertaken for each cluster. K-means, hierarchical agglomerative and spectral analysis methods are used to establish the wind turbine clustering models. The Silhouette Coefficient, Calinski-Harabaz index and within-between index are proposed as criteria to evaluate the effectiveness of the established clustering models. Based on different clustering methods and schemes, various clustering databases are built for clustering pre-calculated CFD (CPCC)-based short-term WPF. For the wind farm case studied, clustering evaluation criteria show that hierarchical agglomerative clustering has reasonable results, spectral clustering is better and K-means gives the best performance. The WPF results produced by different clustering databases also prove the effectiveness of the three evaluation criteria in turn. The newly developed CPCC model has a much higher WPF accuracy than the CPFF model without using clustering techniques, both on temporal and spatial scales. The research provides supports for both the development and improvement of short-term physical WPF systems.

AB - To meet the increasing wind power forecasting (WPF) demands of newly built wind farms without historical data, physical WPF methods are widely used. The computational fluid dynamics (CFD) pre-calculated flow fields (CPFF)-based WPF is a promising physical approach, which can balance well the competing demands of computational efficiency and accuracy. To enhance its adaptability for wind farms in complex terrain, a WPF method combining wind turbine clustering with CPFF is first proposed where the wind turbines in the wind farm are clustered and a forecasting is undertaken for each cluster. K-means, hierarchical agglomerative and spectral analysis methods are used to establish the wind turbine clustering models. The Silhouette Coefficient, Calinski-Harabaz index and within-between index are proposed as criteria to evaluate the effectiveness of the established clustering models. Based on different clustering methods and schemes, various clustering databases are built for clustering pre-calculated CFD (CPCC)-based short-term WPF. For the wind farm case studied, clustering evaluation criteria show that hierarchical agglomerative clustering has reasonable results, spectral clustering is better and K-means gives the best performance. The WPF results produced by different clustering databases also prove the effectiveness of the three evaluation criteria in turn. The newly developed CPCC model has a much higher WPF accuracy than the CPFF model without using clustering techniques, both on temporal and spatial scales. The research provides supports for both the development and improvement of short-term physical WPF systems.

KW - wind turbine

KW - clustering model

KW - computational fluid dynamics

KW - pre-calculated database

KW - wind power forecasting

U2 - 10.3390/en11040854

DO - 10.3390/en11040854

M3 - Article

VL - 11

JO - Energies

T2 - Energies

JF - Energies

SN - 1996-1073

IS - 4

M1 - 854

ER -