Abstract
One of the most important challenges in the field of wind turbines is the modeling of the power curve, since it serves as an adequate indicator of their performance and state of health. This curve relates the electrical power generated by the turbine to the available wind speed. Due to its highly complex nature, one of the approaches to address this issue is through machine learning techniques. In this paper we use epsilon support vector regression (ε-SVR) to predict this power curve. Equally important to the model is the uncertainty associated with this prediction. To estimate the uncertainty, probabilistic analysis of the model residuals is applied. This model has been compared with the Gaussian process regression (GPR) model, widely used in various scientific fields. The results show that the ε-SVR model with uncertainty estimation is able to faithfully characterize the shape of the power curve and the corresponding prediction uncertainty. Furthermore, this model improves the results obtained with GPR in terms of some evaluation metrics, while achieving a better adjustment of the uncertainty and requiring a lower computational cost.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Strategic Energy Technology Information System (SETIS). https://setis.ec.europa.eu/index_en. Last accessed 01 Jul 2023
Zhou, B., Zhang, Z., Li, G., Yang, D., Santos, M.: Review of key technologies for offshore floating wind power generation. Energies 16(2), 710 (2023)
Sierra-García, J.E., Santos, M.: Redes neuronales y aprendizaje por refuerzo en el control de turbinas eólicas. Revista Iberoamericana de Automática e Informática industrial 18(4), 327–335 (2021)
Pandit, R., Astolfi, D., Hong, J., Infield, D., Santos, M.: SCADA data for wind turbine data-driven condition/performance monitoring: a review on state-of-art, challenges and future trends. Wind Eng. 47(2), 422–441 (2023)
Uluyol, O., Parthasarathy, G., Foslien, W., Kim, K.: Power curve analytic for wind turbine performance monitoring and prognostics. In: Annual Conference of the PHM Society, vol. 3, no. 1 (2011)
Barthelmie, R.J., Murray, F., Pryor, S.C.: The economic benefit of short-term forecasting for wind energy in the UK electricity market. Energy Policy 36(5), 1687–1696 (2008)
Gray, C.S., Watson, S.J.: Physics of failure approach to wind turbine condition based maintenance. Wind Energy 13(5), 395–405 (2010). https://doi.org/10.1002/we.360
Pandit, R., Infield, D., Santos, M.: Accounting for environmental conditions in data-driven wind turbine power models. IEEE Trans. Sustain. Energy 14(1), 168–177 (2022)
Long, H., Wang, L., Zhang, Z., Song, Z., Xu, J.: Data-driven wind turbine power generation performance monitoring. IEEE Trans. Ind. Electron. 62(10), 6627–6635 (2015)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. The MIT Press. ISBN 0–262–18253-X (2006)
Pandit, R., Infield, D.: Gaussian process operational curves for wind turbine condition monitoring. Energies 11(7), 1631 (2018)
Gill, S., Stephen, B., Galloway, S.: Wind turbine condition assessment through power curve copula modeling. IEEE Trans. Sustain. Energy 3(1), 94–101 (2012)
Marvuglia, A., Messineo, A.: Monitoring of wind farms’ power curves using machine learning techniques. Appl. Energy 98, 574–583 (2012)
Vidal, Y., Pozo, F., Tutivén, C.: Wind turbine multi-fault detection and classification based on SCADA data. Energies 11(11), 3018 (2018)
Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer-Verlag, New York (1995)
Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14(3), 199–222 (2004)
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011)
Lin, C.-J., Weng, R.C.: Simple probabilistic predictions for support vector regression. Technical report, Department of Computer Science, National Taiwan University (2004)
Penmanshiel Wind Farm Data. https://doi.org/10.5281/zenodo.5946808. Last accessed 01 Jul 2023
International Electrotechnical Commission.: Wind energy generation systems—Part 12–1: Power performance measurements of electricity producing wind turbines. International Electrotechnical Commission (IEC), IEC Central Office, vol. 3, pp. 2017–03 (2017)
Ramos-Teodoro, J., Rodríguez, F.: Distributed energy production, control and management: a review of terminology and common approaches. Revista Iberoamericana de Automática e Informática industrial 19(3), 233–253 (2022)
Acknowledgments
This work has been partially supported by the Spanish Ministry of Science and Innovation under project MCI/AEI/FEDER number PID2021-123543OB-C21.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
García-Vaca, M.Á., Sierra-García, J.E., Santos, M. (2023). Prediction and Uncertainty Estimation in Power Curves of Wind Turbines Using ε-SVR. In: Quaresma, P., Camacho, D., Yin, H., Gonçalves, T., Julian, V., Tallón-Ballesteros, A.J. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2023. IDEAL 2023. Lecture Notes in Computer Science, vol 14404. Springer, Cham. https://doi.org/10.1007/978-3-031-48232-8_46
Download citation
DOI: https://doi.org/10.1007/978-3-031-48232-8_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48231-1
Online ISBN: 978-3-031-48232-8
eBook Packages: Computer ScienceComputer Science (R0)