{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T05:23:10Z","timestamp":1789708990501,"version":"4.0.1"},"reference-count":49,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2020,5,26]],"date-time":"2020-05-26T00:00:00Z","timestamp":1590451200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"DST-CSIR National e-Science Postgraduate Teaching and Training  Platform (NEPTTP). www.escience.ac.za","award":["NEPTTP"],"award-info":[{"award-number":["NEPTTP"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Wind offers an environmentally sustainable energy resource that has seen increasing global adoption in recent years. However, its intermittent, unstable and stochastic nature hampers its representation among other renewable energy sources. This work addresses the forecasting of wind speed, a primary input needed for wind energy generation, using data obtained from the South African Wind Atlas Project. Forecasting is carried out on a two days ahead time horizon. We investigate the predictive performance of artificial neural networks (ANN) trained with Bayesian regularisation, decision trees based stochastic gradient boosting (SGB) and generalised additive models (GAMs). The results of the comparative analysis suggest that ANN displays superior predictive performance based on root mean square error (RMSE). In contrast, SGB shows outperformance in terms of mean average error (MAE) and the related mean average percentage error (MAPE). A further comparison of two forecast combination methods involving the linear and additive quantile regression averaging show the latter forecast combination method as yielding lower prediction accuracy. The additive quantile regression averaging based prediction intervals also show outperformance in terms of validity, reliability, quality and accuracy. Interval combination methods show the median method as better than its pure average counterpart. Point forecasts combination and interval forecasting methods are found to improve forecast performance.<\/jats:p>","DOI":"10.3390\/a13060132","type":"journal-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T05:35:52Z","timestamp":1590557752000},"page":"132","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Short-Term Wind Speed Forecasting Using Statistical and Machine Learning Methods"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0875-4240","authenticated-orcid":false,"given":"Lucky","family":"Daniel","sequence":"first","affiliation":[{"name":"Department of Statistics, University of Venda Private Bag X5050, Thohoyandou 0950, South Africa"},{"name":"DST-CSIR National e-Science Postgraduate Teaching and Training Platform (NEPTTP), LG07, Mathematical Sciences Building, West Campus, Private Bag 3, Wits 2050, Gauteng, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7406-5291","authenticated-orcid":false,"given":"Caston","family":"Sigauke","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Venda Private Bag X5050, Thohoyandou 0950, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6995-605X","authenticated-orcid":false,"given":"Colin","family":"Chibaya","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Technology, Sol Plaatje University, Kimberley 8300, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7337-9176","authenticated-orcid":false,"given":"Rendani","family":"Mbuvha","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Witwatersrand, Private Bag 3, Wits 2050, Gauteng, South Africa"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,5,26]]},"reference":[{"key":"ref_1","unstructured":"Lin, T.C. (2007). Application of Artificial Neural Network and Genetic Algorithm to Forecasting of Wind Power Output. [Master\u2019s Thesis, University of Jyv\u00e4skyl\u00e4]."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Chen, Q., and Folly, K.A. (2018, January 8\u201313). Comparison of Three Methods for Short-Term Wind Power Forecasting. Proceedings of the IEEE 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.","DOI":"10.1109\/IJCNN.2018.8489472"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1214\/13-STS445","article-title":"Wind energy: Forecasting challenges for its operational management","volume":"28","author":"Pinson","year":"2013","journal-title":"Stat. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Barbosa de Alencar, D., de Mattos Affonso, C., Lim ao de Oliveira, R., Moya Rodr\u00edguez, J., Leite, J., and Reston Filho, J. (2017). Different models for forecasting wind power generation: Case study. Energies, 10.","DOI":"10.3390\/en10121976"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.egypro.2017.12.071","article-title":"Short-term wind power forecasting using wavelet-based neural network","volume":"142","author":"Abhinav","year":"2017","journal-title":"Energy Procedia"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1016\/j.egyr.2019.05.007","article-title":"Short-term forecast of wind speed through mathematical models","volume":"5","author":"Ferreira","year":"2019","journal-title":"Energy Rep."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Morina, M., Grimaccia, F., Leva, S., and Mussetta, M. (2016, January 24\u201329). Hybrid weather-based ANN for forecasting the production of a real wind power plant. Proceedings of the IEEE 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727858"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Giebel, G., and Kariniotakis, G. (2017). Wind power forecasting\u2014A review of the state of the art. Renewable Energy Forecasting, Elsevier.","DOI":"10.1016\/B978-0-08-100504-0.00003-2"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Verma, S.M., Reddy, V., Verma, K., and Kumar, R. (2018, January 22\u201323). Markov Models Based Short Term Forecasting of Wind Speed for Estimating Day-Ahead Wind Power. Proceedings of the IEEE 2018 International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), Chennai, India.","DOI":"10.1109\/ICPECTS.2018.8521645"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2513","DOI":"10.1016\/j.enpol.2008.03.011","article-title":"Grappling with a half-hearted policy: The case of renewable energy and the environment in South Africa","volume":"36","author":"Sebitosi","year":"2008","journal-title":"Energy Policy"},{"key":"ref_11","unstructured":"Yan, J., Liu, Y., Han, S., Gu, C., and Li, F. (2014, January 24\u201325). A robust probabilistic wind power forecasting method considering wind scenarios. Proceedings of the 3rd Renewable Power Generation Conference (RPG 2014), Naples, Italy."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sigauke, C., Nemukula, M., and Maposa, D. (2018). Probabilistic Hourly Load Forecasting Using Additive Quantile Regression Models. Energies, 11.","DOI":"10.3390\/en11092208"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.aasri.2012.09.023","article-title":"A statistical approach of wind power forecasting for grid scale","volume":"2","author":"Chen","year":"2012","journal-title":"AASRI Procedia"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.proenv.2012.01.256","article-title":"A prediction model for wind farm power generation based on fuzzy modeling","volume":"12","author":"Zhu","year":"2012","journal-title":"Procedia Environ. Sci."},{"key":"ref_15","unstructured":"Baghirli, O. (2015). Comparison of Lavenberg-Marquardt, Scaled Conjugate Gradient and Bayesian Regularization Backpropagation Algorithms for Multistep Ahead Wind Speed Forecasting Using Multilayer Perceptron Feedforward Neural Network. [Master\u2019s Thesis, Uppsala University]."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Mbuvha, R. (2017). Bayesian Neural Networks for Short Term Wind Power Forecasting. [Master\u2019s Thesis, School of Computer Science and Communication, KTH Royal Institute of Technology].","DOI":"10.1109\/ICRERA.2017.8191129"},{"key":"ref_17","first-page":"730","article-title":"Probabilistic load forecasting via quantile regression averaging on sister forecasts","volume":"8","author":"Liu","year":"2015","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.asoc.2018.02.004","article-title":"Optimal forecast combination based on neural networks for time series forecasting","volume":"66","author":"Wang","year":"2018","journal-title":"Appl. Soft Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1007\/s00180-014-0523-0","article-title":"Computing electricity spot price prediction intervals using quantile regression and forecast averaging","volume":"30","author":"Nowotarski","year":"2015","journal-title":"Comput. Stat."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5120704","DOI":"10.1155\/2017\/5120704","article-title":"Prediction interval construction for byproduct gas flow forecasting using optimized twin extreme learning machine","volume":"2017","author":"Sun","year":"2017","journal-title":"Math. Probl. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shen, Y., Wang, X., and Chen, J. (2018). Wind power forecasting using multi-objective evolutionary algorithms for wavelet neural network-optimized prediction intervals. Appl. Sci., 8.","DOI":"10.3390\/app8020185"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Abuella, M., and Chowdhury, B. (2017, January 17\u201319). Hourly probabilistic forecasting of solar power. Proceedings of the IEEE 2017 North American Power Symposium (NAPS), Morgantown, WV, USA.","DOI":"10.1109\/NAPS.2017.8107270"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.rser.2014.01.033","article-title":"Review on probabilistic forecasting of wind power generation","volume":"32","author":"Zhang","year":"2014","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_24","unstructured":"Liu, H. (2008). Generalized Additive Model, Department of Mathematics and Statistics University of Minnesota Duluth."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1109\/TSG.2013.2278425","article-title":"Local short and middle term electricity load forecasting with semi-parametric additive models","volume":"5","author":"Goude","year":"2014","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_26","unstructured":"Pierrot, A., and Goude, Y. (2011, January 25\u201328). Short-term electricity load forecasting with generalized additive models. Proceedings of the ISAP Power, Hersonissos, Greece."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1080\/01621459.2012.722900","article-title":"Modeling and forecasting daily electricity load curves: A hybrid approach","volume":"108","author":"Cho","year":"2013","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.jsp.2013.11.004","article-title":"Using generalized additive (mixed) models to analyze single case designs","volume":"52","author":"Shadish","year":"2014","journal-title":"J. Sch. Psychol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/S0169-2070(97)00044-7","article-title":"Forecasting with artificial neural networks: The state of the art","volume":"14","author":"Zhang","year":"1998","journal-title":"Int. J. Forecast."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","article-title":"Stochastic gradient boosting","volume":"38","author":"Friedman","year":"2002","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Mpfumali, P., Sigauke, C., Bere, A., and Mulaudzi, S. (2019). Day Ahead Hourly Global Horizontal Irradiance Forecasting\u2014Application to South African Data. Energies, 12.","DOI":"10.3390\/en12183569"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/BF02985802","article-title":"The elements of statistical learning: Data mining, inference and prediction","volume":"27","author":"Hastie","year":"2005","journal-title":"Math. Intell."},{"key":"ref_34","unstructured":"Hastie, T., and Tibshirani, R. (1990). Generalized Additive Models, CRC Press."},{"key":"ref_35","unstructured":"Pya, N., and Wood, S.N. (2016). A note on basis dimension selection in generalized additive modelling. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1057\/jors.1969.103","article-title":"The combination of forecasts","volume":"20","author":"Bates","year":"1969","journal-title":"J. Oper. Res. Soc."},{"key":"ref_37","first-page":"382","article-title":"Bayesian model averaging: A tutorial","volume":"14","author":"Hoeting","year":"1999","journal-title":"Stat. Sci."},{"key":"ref_38","first-page":"54","article-title":"Forecasting medium-term electricity demand in a South African electric power supply system","volume":"28","author":"Sigauke","year":"2017","journal-title":"J Energy S. Afr."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2448","DOI":"10.1109\/TSG.2016.2527820","article-title":"Forecasting uncertainty in electricity smart meter data by boosting additive quantile regression","volume":"7","author":"Taieb","year":"2016","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1016\/j.ijforecast.2014.12.004","article-title":"Probabilistic forecasting of electricity spot prices using Factor Quantile Regression Averaging","volume":"32","author":"Maciejowska","year":"2016","journal-title":"Int. J. Forecast."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1016\/j.ijforecast.2015.12.001","article-title":"Additive models and robust aggregation for GEFCom2014 probabilistic electric load and electricity price forecasting","volume":"32","author":"Gaillard","year":"2016","journal-title":"Int. J. Forecast."},{"key":"ref_42","unstructured":"Fasiolo, M., Goude, Y., Nedellec, R., and Wood, S.N. (2017). Fast calibrated additive quantile regression. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3664","DOI":"10.1109\/TSG.2018.2833869","article-title":"Combining probabilistic load forecasts","volume":"10","author":"Wang","year":"2018","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1080\/10618600.2014.938812","article-title":"Learning interactions via hierarchical group-Lasso regularization","volume":"24","author":"Lim","year":"2015","journal-title":"J. Comput. Graph. Stat."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., and Wainwright, M. (2015). Statistical Learning with Sparsity: The Lasso and Generalizations, Chapman and Hall\/CRC.","DOI":"10.1201\/b18401"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1109\/TIT.2016.2517008","article-title":"The generalized Lasso with non-linear observations","volume":"62","author":"Plan","year":"2016","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1184","DOI":"10.1175\/1520-0450(1984)023<1184:TSMTSA>2.0.CO;2","article-title":"Time series models to simulate and forecast wind speed and wind power","volume":"23","author":"Brown","year":"1984","journal-title":"J. Clim. Appl. Meteorol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/S0167-6105(98)00192-5","article-title":"Short-term prediction of the power production from wind farms","volume":"80","author":"Landberg","year":"1999","journal-title":"J. Wind. Eng. Ind. Aerodyn."},{"key":"ref_49","unstructured":"Olaofe, Z.O. (2013). Wind Energy Generation and Forecasts: A Case Study of Darling and Vredenburg Sites. [Ph.D. Thesis, University of Cape Town]."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/13\/6\/132\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:32:40Z","timestamp":1760175160000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/13\/6\/132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,26]]},"references-count":49,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["a13060132"],"URL":"https:\/\/doi.org\/10.3390\/a13060132","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,26]]}}}