Journal Home > Volume 9 , Issue 4
CSEE Journal of Power and Energy Systems 2023, 9(4): 1460-1471 https://doi.org/10.17775/CSEEJPES.2022.01960
Regular Paper | Open Access | Issue | Published: 18 August 2022

Transfer Strategy for Power Output Estimation of Wind Farm at Planning Stage Based on a SVR Model

Show Author's Information Zihao Li1,  Wei Sun1,  Yue Xiang2,  Gareth P. Harrison1( )
School of Engineering, University of Edinburgh, Edinburgh, EH9 3DW, UK
College of Electrical Engineering, Sichuan University, Chengdu 610065, China
Keywords:
Machine learning, wind farm, model transfer strategy, power curve, power output estimation
Cite this article:
Li Z, Sun W, Xiang Y, et al. Transfer Strategy for Power Output Estimation of Wind Farm at Planning Stage Based on a SVR Model. CSEE Journal of Power and Energy Systems, 2023, 9(4): 1460-1471. https://doi.org/10.17775/CSEEJPES.2022.01960
Download citation
EndNote(RIS)
BibTeX

260

Views

10

Downloads

Citations

0

Crossref

1

WoS

1

Scopus

0

CSCD

Abstract Full text About this article

The conventional wind farm (WF) power generation modelling method highly relies on wind hindcast produced by record time-series data or numerical weather modelling. However, estimating production at future sites is challenging in the absence of local wind monitoring. To address this, a data-driven WF modelling and model transfer strategy is proposed in this work. It considers the challenge of how to transpose metered data from existing operational WFs to sites that might feature as a prospective site for a new WF. By modelling 14 WFs distributed across Scotland using a machine learning (ML) approach, this study proved it was possible to effectively model metered production at a site using modelled wind speed and direction. In addition, this study also found when the latitude difference between two WFs is less than 0.2 degrees and the distance is less than 50 km, two WFs in non-mountainous areas can share an ML model. The results of the shared ML model remain superior to the results of the given power curve from manufacturers, after adjusting the results by the ratio of the power curve in these two WFs. The WF model transfer strategy investigated in this work offered a novel approach to transposing WF production estimates to new sites and appeared to offer better value than simple power curves, which is of importance at the early planning stage for site selection, although it would likely not fully replace detailed micro-siting modelling which are well established in the industry.


menu
Abstract
Full text
Outline
About this article

Transfer Strategy for Power Output Estimation of Wind Farm at Planning Stage Based on a SVR Model

Show Author's information Zihao Li1, Wei Sun1, Yue Xiang2, Gareth P. Harrison1( )
School of Engineering, University of Edinburgh, Edinburgh, EH9 3DW, UK
College of Electrical Engineering, Sichuan University, Chengdu 610065, China

Abstract

The conventional wind farm (WF) power generation modelling method highly relies on wind hindcast produced by record time-series data or numerical weather modelling. However, estimating production at future sites is challenging in the absence of local wind monitoring. To address this, a data-driven WF modelling and model transfer strategy is proposed in this work. It considers the challenge of how to transpose metered data from existing operational WFs to sites that might feature as a prospective site for a new WF. By modelling 14 WFs distributed across Scotland using a machine learning (ML) approach, this study proved it was possible to effectively model metered production at a site using modelled wind speed and direction. In addition, this study also found when the latitude difference between two WFs is less than 0.2 degrees and the distance is less than 50 km, two WFs in non-mountainous areas can share an ML model. The results of the shared ML model remain superior to the results of the given power curve from manufacturers, after adjusting the results by the ratio of the power curve in these two WFs. The WF model transfer strategy investigated in this work offered a novel approach to transposing WF production estimates to new sites and appeared to offer better value than simple power curves, which is of importance at the early planning stage for site selection, although it would likely not fully replace detailed micro-siting modelling which are well established in the industry.

Keywords: Machine learning, wind farm, model transfer strategy, power curve, power output estimation

References(40)

[1]

P. Walker, R. Mason, and D. Carrington, “Theresa May commits to net zero UK carbon emissions by 2050,” The Guardian, 2019
Google Scholar
[2]
BEIS. (2020, Oct. 22). Department for Business, Energy & Industrial Strategy. Energy consumption in the UK 2020. [Online]. Available: https://www.gov.uk/government/statistics/energy-consumption-in-the-uk-2020.
[3]

W. Sun and G. P. Harrison, “Wind-solar complementarity and effective use of distribution network capacity,” Applied Energy, vol. 247, pp. 89–101, Aug. 2019.
DOI Google Scholar
[4]
BEIS. (2020, Dec. 14). Department for Business, Energy & Industrial Strategy. Modelling 2050-Electricity System Analysis. 2018. [Online]. Available: https://www.gov.uk/government/publications/modelling-2050-electricity-system-analysis.
[5]

X. C. Wang, P. Guo, and X. B. Huang, “A review of wind power forecasting models,” Energy Procedia, vol. 12, pp. 770–778, Dec. 2011.
DOI Google Scholar
[6]

S. A. Vargas, G. R. T. Esteves, P. M. Maçaira, B. Q. Bastos, F. L. C. Oliveira, and R. C. Souza, “Wind power generation: a review and a research agenda,” Journal of Cleaner Production, vol. 218, pp. 850–870, May 2019.
DOI Google Scholar
[7]
Y. H. Wan, E. Ela, and K. Orwig, “Development of an equivalent wind plant power-curve,” National Renewable Energy Lab., Golden, No. NREL/CP-550–48146, 2010.
[8]
B. P. Hayes, I. S. Ilie, A. Porpodas, S. Z. Djokic, and G. Chicco, “Equivalent power curve model of a wind farm based on field measurement data,” in 2011 IEEE Trondheim PowerTech, 2011, pp. 1–7.
DOI
[9]

S. Wharton and J. K. Lundquist, “Assessing atmospheric stability and its impacts on rotor-disk wind characteristics at an onshore wind farm,” Wind Energy, vol. 15, no. 4, pp. 525–546, May 2012.
DOI Google Scholar
[10]
T. D. Jin and Z. G. Tian, “Uncertainty analysis for wind energy production with dynamic power curves,” in 2010 IEEE 11th International Conference on Probabilistic Methods Applied to Power Systems, 2010, pp. 745–750.
[11]

A. M. Foley, P. G. Leahy, A. Marvuglia, and E. J. McKeogh, “Current methods and advances in forecasting of wind power generation,” Renewable Energy, vol. 37, no. 1, pp. 1–8, Jan. 2012.
DOI Google Scholar
[12]

Y. C. Deng, X. H. Tang, Z. Y. Zhou, Y. Yang, and F. Niu, “Application of machine learning algorithms in wind power: a review,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2021, doi: 10.1080/15567036.2020.1869867.
DOI Google Scholar
[13]

A. Marvuglia and A. Messineo, “Monitoring of wind farms' power curves using machine learning techniques,” Applied Energy, vol. 98, pp. 574–583, Oct. 2012.
DOI Google Scholar
[14]
D. He and R. Y. Liu, “Ultra-short-term wind power prediction using ANN ensemble based on PCA,” in Proceedings of the 7th International Power Electronics and Motion Control Conference, 2012, pp. 2108–2112.
[15]

X. X. Yin and X. W. Zhao, “Big data driven multi-objective predictions for offshore wind farm based on machine learning algorithms,” Energy, vol. 186, pp. 115704, Nov. 2019.
DOI Google Scholar
[16]

A. Simão, P. J. Densham, and M. M. Haklay, “Web-based GIS for collaborative planning and public participation: an application to the strategic planning of wind farm sites,” Journal of Environmental Management, vol. 90, no. 6, pp. 2027–2040, May 2009.
DOI Google Scholar
[17]

L. Lledó, V. Torralba, A. Soret, J. Ramon, and F. J. Doblas-Reyes, “Seasonal forecasts of wind power generation,” Renewable Energy, vol. 143, pp. 91–100, Dec. 2019.
DOI Google Scholar
[18]

M. C. Alexiadis, P. S. Dokopoulos, H. S. Sahsamanoglou, “Wind speed and power forecasting based on spatial correlation models,” IEEE Transactions on Energy Conversion, vol. 14, no. 3, pp. 836–842, Sep. 1999.
DOI Google Scholar
[19]

G. R. Ren, J. Wan, J. F. Liu, and D. R. Yu, “Spatial and temporal correlation analysis of wind power between different provinces in China,” Energy, 191, pp. 116514, Jan. 2020.
DOI Google Scholar
[20]

F. Li, G. R. Ren, and J. Lee, “Multi-step wind speed prediction based on turbulence intensity and hybrid deep neural networks,” Energy Conversion and Management, vol. 186, pp. 306–322, Apr. 2019.
DOI Google Scholar
[21]

A. A. Ezzat, M. Jun, and Y. Ding, “Spatio-temporal asymmetry of local wind fields and its impact on short-term wind forecasting,” IEEE Transactions on Sustainable Energy, vol. 9, no. 3, pp. 1437–1447, Jul. 2018.
DOI Google Scholar
[22]

A. D. Sahin and Z. Sen, “Wind energy directional spatial correlation functions and application for prediction,” Wind Engineering, vol. 24, no. 3, pp. 223–231, May 2000.
DOI Google Scholar
[23]

I. G. Damousis, M. C. Alexiadis, J. B. Theocharis, and P. S. Dokopoulos, “A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation,” IEEE Transactions on Energy Conversion, vol. 19, no. 2, pp. 352–361, Jun. 2004.
DOI Google Scholar
[24]
G. Czisch and B. Ernst, “High wind power penetration by the systematic use of smoothing effects within huge catchment areas shown in a European example,” Proceedings of WINDPOWER 2001, American Wind Energy Association, Washington, DC (2001).
[25]
G. Papaefthymiou and P. Pinson, “Modeling of spatial dependence in wind power forecast uncertainty” in Proceedings of the 10th International Conference on Probablistic Methods Applied to Power Systems, 2008, pp. 1–9.
[26]
M. Ali, I. S. Ilie, J. V. Milanović, and G. Chicco, “Probabilistic clustering of wind generators,” in IEEE PES General Meeting, 2010, pp. 1–6.
DOI
[27]

R. Girard and D. Allard, “Spatio-temporal propagation of wind power prediction errors,” Wind Energy, vol. 16, no. 7, pp. 999–1012, Oct. 2013.
DOI Google Scholar
[28]
N. Siebert and G. N. Kariniotakis, “Reference wind farm selection for regional wind power prediction models,” in European Wind Energy Conference, EWEC 2006, 2006, pp. 10.
[29]
T. Ishihara, A. Yamaguchi, T. Ogawa, K. Sakai, and Y. Fujino, “An upscaling approach for the regional wind power forecasting,” In: European Wind Energy Conference and Exhibition. Brussels, Belgium, pp. 948–951 (2007).
[30]

M. Lange, “On the uncertainty of wind power predictions—Analysis of the forecast accuracy and statistical distribution of errors,” Journal of Solar Energy Engineering, vol. 127, no. 2, pp. 177–184, May 2005.
DOI Google Scholar
[31]

W. Teng, X. Wang, Y. Meng and W. Shi, “An improved support vector clustering approach to dynamic aggregation of large wind farms,” CSEE Journal of Power and Energy Systems, vol. 5, no. 2, pp. 215–223, Jun. 2019.
DOI Google Scholar
[32]

W. S. Noble, “What is a support vector machine?,” Nature Biotechnology, vol. 24, no. 12, pp. 1565–1567, Dec. 2006.
DOI Google Scholar
[33]

A. J. Smola and B. Schölkopf, “A tutorial on support vector regression,” Statistics and Computing, vol. 14, no. 3, pp. 199–222, Aug. 2004.
DOI Google Scholar
[34]
MathWorks. (2019, Aug. 13). Fit a support vector machine regression model—MATLAB Fitrsvm-MathWorks United Kingdom. [Online]. Available: https://uk.mathworks.com/help/stats/fitrsvm.html.
[35]
Wind Energy Generation Systems-Part 12–1: Power Performance Measurements of Electricity Producing Wind Turbines, IEC 61400-12-1-2017, 2017.
[36]
S. Hawkins and G. Harrison, “A reanalysis of UK wind speeds using the WRF mesoscale model,” in European Wind Energy Conference and Exhibition, 2010.
[37]

G. P. Harrison, S. L. Hawkins, D. Eager, and L. C. Cradden, “Capacity value of offshore wind in Great Britain,” Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, vol. 229, no. 5, pp. 360–372, Oct. 2015.
DOI Google Scholar
[38]
G. Harrison. (2020, Sep. 25). Prof Gareth Harrison — School of Engineering. [Online]. Available: https://www.eng.ed.ac.uk/about/people/prof-gareth-harrison.
[39]

Z. H. Li, D. Friedrich, and G. P. Harrison, “Demand forecasting for a mixed-use building using agent-schedule information with a data-driven model,” Energies, vol. 13, no. 4, pp. 780, Feb. 2020.
DOI Google Scholar
[40]
S. L. Hawkins, “High resolution reanalysis of wind speeds over the British Isles for wind energy integration,” Ph.D. dissertation, University of Edinburgh, Edinburgh, 2012
Publication history
Copyright
Rights and permissions

Publication history

Received: 28 March 2022
Revised: 03 May 2022
Accepted: 02 June 2022
Published: 18 August 2022
Issue date: July 2023

Copyright

© 2022 CSEE.

Rights and permissions

This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Return