10.1007/s40095-020-00352-2

Artificially intelligent models for the site-specific performance of wind turbines

XML HTML PDF
  • R. Veena1,
  • S. Mathew*2,
  • M. I. Petra1,
  1. Institute of Applied Data Analytics, Universiti Brunei Darussalam, Gadong, 1410, BN
  2. Faculty of Engineering and Science, University of Agder, Grimstad, 4879, NO
Cover Image

Published in Issue 2020-07-08

How to Cite

Veena, R., Mathew, S., & Petra, M. I. (2020). Artificially intelligent models for the site-specific performance of wind turbines. International Journal of Energy and Environmental Engineering, 11(3 (September 2020). https://doi.org/10.1007/s40095-020-00352-2
Crossref
Scopus
Google Scholar
Europe PMC

HTML views: 40

PDF views: 113

Abstract

Abstract Power developed by the wind turbines, at different wind velocities, is a key information required for the successful design and efficient management of wind energy projects. Conventionally, for these applications, manufacturer’s power curves are used in estimating the velocity–power characteristics of the turbines. However, performance of the turbines under actual field environments may significantly differ from the manufacturer’s power curves, which are derived under ‘standard’ conditions. In case of existing wind projects with sufficient performance data, the velocity–power variations can better be defined using artificially intelligent models. In this paper, we compare the performance of four such models by applying them to a 2-MW onshore wind turbine. Models based on ANN, KNN, SVM and MARS were developed and tested using the SCADA data collected from the turbine. All the AI models performed significantly better than the manufacturer’s power curve. Among the AI methods, SVM-based predictions showed the highest accuracy. A site-specific performance curve for the turbine, based on the SVM model, is presented. Wider adaptability of this approach has been demonstrated by successfully implementing the model for a 3.6-MW wind turbine, working under offshore environment. Being “site-specific data” driven, the proposed models are more accurate and hence better choice for applications like short-term wind power forecasting and pro-diagnostics of wind turbines.

Keywords

  • Artificial intelligence,
  • Data-driven models,
  • Power curve,
  • Wind power forecasts,
  • Wind turbine prognostics
HTML PDF

References

  1. Global Wind Energy Council, Global Wind Report 2019.
  2. https://gwec.net/global-wind-report-2019/
  3. Accessed 12 May 2020
  4. Global Wind Energy Council, Wind Power to dominate power sector growth.
  5. https://gwec.net/publications/global-wind-energy-outlook/global-wind-energy-outlook-2016/
  6. ; (2016). Accessed 8 June 2018
  7. IEC: Wind turbine generator systems pt. 12: wind turbine power performance testing. International Electrotechnical Commission Standard IEC 61400 (1998)
  8. Mathew (2006) Springer
  9. Clifton and Wagner (2014) Accounting for the effect of turbulence on wind turbine power curves 524(1)
  10. Brower, M.C.: Wind Turbine Performance: Issues and Evidence,
  11. https://www.ewea.org/events/workshops/wp-content/uploads/proceedings/Analysis_of_Operating_Wind_farms/EWEA%2520Workshop%2520Lyon%2520-%25205-2%2520Michael%2520Brower%2520AWS%2520Truepower.pdf/
  12. ; (2012). Accessed 8 Jun 2018
  13. Brown, C.: Fast Verification of Wind Turbine Power Curves: Summary of Project Results. Master’s thesis, Technical University of Denmark, (2012)
  14. Tindal, A., Johnson, C., LeBlanc, M., Harman, K., Rareshide, E., Graves, A.: Site-Specific Adjustments to Wind Turbine Power Curves. In: Proceedings of the AWEA Wind power Conference, (2008)
  15. Jin, T., Tian, Z.: Uncertainty analysis for wind energy production with dynamic power curves. In: Proceedings of the IEEE International conference in probabilistic methods applied to power systems, pp 745–750, (2010)
  16. Albers, A., Jakobi, T., Rohden, R., Stoltenjohannes, J.: Influence of meteorological variables on measured wind turbine power curves. In: Proceedings of the European Wind Energy Conference and Exhibition, pp 525–546, (2007)
  17. Wagner et al. (2009) The influence of the wind speed profile on wind turbine performance measurement 12(4) (pp. 348-362)
  18. Ciulla et al. (2019) Modelling and analysis of real-world wind turbine power curves: assessing deviations from nominal curve by neural networks (pp. 477-492)
  19. Manobel et al. (2018) Wind turbine power curve modeling based on Gaussian processes and artificial neural networks (pp. 1015-1020)
  20. Pelletier et al. (2016) Wind turbine power curve modelling using artificial neural network (pp. 207-214)
  21. Schlechtingen et al. (2013) Using data-mining approaches for wind turbine power curve monitoring: a comparative study 4(3) (pp. 671-679)
  22. Lydia et al. (2013) Advanced algorithms for wind turbine power curve modeling 4(3) (pp. 827-835)
  23. Janssens et al. (2016) Data-driven multivariate power curve modeling of offshore wind turbines (pp. 331-338)
  24. Kusiak et al. (2009) On-line monitoring of power curves 34(6) (pp. 1487-1493)
  25. Pandit et al. (2019) Comparison of advanced non-parametric models for wind turbine power curves 13(9) (pp. 1503-1510)
  26. Pei and Li (2019) Wind turbine power curve modeling with a hybrid machine learning technique 9(22)
  27. Ouyang et al. (2017) Modeling wind-turbine power curve: a data partitioning and mining approach (pp. 1-8)
  28. Camelo et al. (2018) Innovative hybrid models for forecasting time series applied in wind generation based on the combination of time series models with artificial neural networks (pp. 347-357)
  29. Koo et al. (2015) Wind-speed prediction and analysis based on geological and distance variables using an artificial neural network: a case study in South Korea 93(2) (pp. 1296-1302)
  30. Hecht-Nielsen (1988) Theory of the backpropagation neural network 1(1) (pp. 445-448)
  31. Cristianini and Shawe-Taylor (2000) Cambridge University Press
  32. Anava, O., Levy, K.:
  33. k
  34. *-nearest neighbors: from global to local. In: Jordan, M.I., LeCun, Y., Solla, S.A. (eds) Advances in Neural Information Processing Systems, pp. 4916–4924 (2016)
  35. Friedman (1991) Multivariate adaptive regression splines 19(1) (pp. 1-141)
  36. Shu-Xian, Z., Xue-Li, Z.: The Comparison with improved mixture kernel SVM and traditional Neural Network. In: Proceedings of the International Conference on Signal Processing Systems, IEEE Xplore, (2010)
  37. Fuqing et al. (2013) A comparative study of artificial neural networks and support vector machine for fault diagnosis 9(1) (pp. 49-60)
  38. Ahmadi and Rodehutscord (2017) Application of artificial neural network and support vector machines in predicting metabolizable energy in compound feeds for pigs 4(27) (pp. 1-8)
  39. Burges (1998) A tutorial on support vector machines for pattern recognition 2(2) (pp. 121-167)
  40. Rychetsky (2001) Shaker Verlag
  41. Taylor and Cristianini (2004) Cambridge University Press
  42. Lange and Focken (2006) Springer
  43. Uluyol, O., Parthasarathy, G., Foslien, W., Kim, K.: Power curve analytic for wind turbine performance monitoring and prognostics. In: Proceedings of the Annual Conference of the Prognostics and Health Management Society, 2,1–8, (2011)