Correo Electrónico
DNINFOA - SIA
Bibliotecas
Convocatorias
Identidad U.N.
Published
To Transform or not to Transform: The Impact of Both Approaches when Predicting wind Power Output as a Percentage of the Installed Capacity
Transformar o no transformar: El impacto de ambos enfoques cuando se predice la potencia eólica como un porcentaje de la capacidad instalada
DOI:
https://doi.org/10.15446/rce.v49n2.123543Keywords:
Bias correction; , Bounded response modeling;, Capacity factor;, Response transformation;, Wind power prediction. (en)Corrección de sesgo;, Factor de capacidad;, Modelación de respuesta acotada; , Predicción potencia eólica;, Transformación de la respuesta. (es)
Downloads
This research comparatively evaluates several statistical and machine learning models to predict normalized wind power output, when applied to a case study of wind power records from the Energy Reliability Council of Texas (ERCOT). The impact on predictive ability derived from two approaches is quantified: (1) modeling the response directly in the [0,1] interval, versus (2) performing a transformation f to some unbounded space. A correction mechanism is proposed to mitigate the bias introduced by the use of the transformation f. The results suggest that combining suitable transformations (v-logit or probit) with bias correction significantly improves wind power prediction, especially when using flexible models like support vector machines (SVM) and generalized additive models (GAM).
Esta investigación evalúa comparativamente varios modelos estadísticos y de aprendizaje automático para predecir la generación eólica normalizada, aplicados a un estudio de caso con registros del Consejo de Confiabilidad Energética de Texas (ERCOT). Se cuantifica el impacto en la capacidad predictiva derivado de dos enfoques: (1) modelar la variable de respuesta directamente en el intervalo [0, 1], y (2) aplicar una transformación f hacia un espacio no acotado. Se propone un mecanismo de corrección para mitigar el sesgo introducido por el uso de dicha transformación f. Los resultados sugieren que combinar transformaciones adecuadas (v-logit o probit) con la corrección de sesgo mejora significativamente la predicción de la potencia eólica, especialmente al emplear modelos flexibles como las máquinas de vectores de soporte (SVM) y los modelos aditivos generalizados (GAM).
References
Arora, P. & Ceferino, L. (2024), 'A quasi-binomial regression model for hurricaneinduced power outages during early warning', ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering 10(2), 04024027.
Arrieta-Prieto, M. & Kristen, R. S. (2021), Data-driven prediction of power at wind farm level, in 'Proceedings of the IISE Annual Conference and Expo 2021', pp. 1076 - 1081.
Arrieta-Prieto, M. & Schell, K. R. (2024), 'Spatially transferable machine learning wind power prediction models: v- logit random forests', Renewable Energy 223, 120066.
Capelletti, M., Fogli, V., Santilli, E., Gardini, M., Vignali, R. & De Nicolao, G. (2025), 'Comparing beta regression and quantile regression forests for probabilistic photovoltaic energy forecasting', IFAC-PapersOnLine 59(1), 325-330.
Capelletti, M., Raimondo, D.M. & De Nicolao, G. (2024), 'Wind power curve modeling: A probabilistic beta regression approach', Renewable Energy 223, 119970.
Cetinay, H., Kekeç, T., Kuipers, F. A. & Tax, D. (2017), Markov random -eld for wind farm planning, in '2017 IEEE International Conference on Smart Energy Grid Engineering (SEGE)', IEEE, pp. 182-187.
Cressie, N. (1993), Statistics for spatial data, John Wiley & Sons.
[dataset] Energy Reliability Council of Texas (ERCOT) (2018), 'ERCOT wind patterns for existing sites, 1980-2017 ', http://www.ercot.com/gridinfo/res ource. Data set.
[dataset] National Wind Institute (2016), 'West Texas Mesonet ', https://www.depts.ttu.edu/nwi/research/facilities/wtm/index.php.
[dataset] Staffell, Iain and Pfenninger, Stefan (2016), 'Renewables.ninja', www.renewables.ninja.
Ezzat, A. A., Jun, M. & Ding, Y. (2018), 'Spatio-temporal asymmetry of local wind fields and its impact on short-term wind forecasting', IEEE Transactions on Sustainable Energy 9(3), 1437-1447.
Ferrari, S. & Cribari-Neto, F. (2004), 'Beta regression for modelling rates and proportions', Journal of applied statistics 31(7), 799-815.
Jacondino, W. D., da Silva Nascimento, A. L., Calvetti, L., Fisch, G., Beneti, C. A. A. & da Paz, S. R. (2021), 'Hourly day-ahead wind power forecasting at two wind farms in northeast Brazil using WRF model', Energy 230, 120841.
Kanoglu, M., Çengel, Y. A. & Cimbala, J. M. (2020), Fundamentals and applications of renewable energy, McGraw-Hill Education.
Kazmi, H. & Tao, Z. (2022), 'How good are tso load and renewable generation forecasts: Learning curves, challenges, and the road ahead', Applied Energy 323, 119565.
Kim, D.-Y. & Kim, B.-S. (2024), 'Exploring wind curtailment effects and economic implications in the growing variable renewable energy penetration', Journal of Renewable and Sustainable Energy 16(2).
McCullagh, P. (1983), 'Quasi-likelihood functions', The Annals of Statistics pp. 59-67.
Neyman, J. & Scott, E. L. (1960), 'Correction for bias introduced by a transformation of variables', The Annals of Mathematical Statistics 31(3), 643-655.
Pinson, P. (2012), 'Very-short-term probabilistic forecasting of wind power with generalized logit normal distributions', Journal of the Royal Statistical Society: Series C (Applied Statistics) 61(4), 555-576.
Premalatha, M., Abbasi, T., Abbasi, S. A. et al. (2014), 'Wind energy: Increasing deployment, rising environmental concerns', Renewable and Sustainable Energy Reviews 31, 270-288.
Pumi, G., Rauber, C. & Bayer, F. M. (2020), 'Kumaraswamy regression model with Aranda-Ordaz link function', Test 29(4), 1051-1071.
Saltyte Benth, J. & Saltyte, L. (2011), 'Spatial temporal model for wind speed in Lithuania', Journal of Applied Statistics 38(6), 1151-1168.
Staid, A., VerHulst, C. & Guikema, S. D. (2018), 'A comparison of methods for assessing power output in non-uniform onshore wind farms', Wind Energy 21(1), 42-52.
Wikle, C. K., Zammit-Mangion, A. & Cressie, N. (2019), Spatio-temporal statistics with R, Chapman and Hall/CRC.
Wu, Y.-K. & Hong, J.-S. (2007), A literature review of wind forecasting technology in the world, in '2007 IEEE Lausanne Power Tech', IEEE, pp. 504-509.
Wytock, M. & Kolter, Z. (2013), Sparse Gaussian conditional random fields: Algorithms, theory, and application to energy forecasting, in 'International conference on machine learning', PMLR, pp. 1265-1273.
Yuan, X., Chen, C., Jiang, M. & Yuan, Y. (2019), 'Prediction interval of wind power using parameter optimized Beta distribution based LSTM model', Applied Soft Computing 82, 105550.
Zhang, Y., Li, Y. & Zhang, G. (2020), 'Short-term wind power forecasting approach based on Seq2Seq model using NWP data', Energy 213, 118371.
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
