Abstract
Wind power ramp events (WPREs) are strong increases or decreases of wind speed in a short period of time. Predicting WPREs in wind farms is of vital importance given that they can produce damages in the turbines, and, in any case, they suddenly affect the wind farm production. In contrast to previous binary definitions of the prediction problem (ramp vs non-ramp), a three-class prediction model is used in this paper, proposing a novel discretization function, able to detect the nature of WPREs: negative ramp, non-ramp and positive ramp events. Moreover, the natural order of these labels is exploited to obtain better results in the prediction of these events. The independent variables used for prediction include, in this case, past wind speed values and meteorological data obtained from physical models (reanalysis data). Reanalysis will be also used for recovering missing data from the measuring stations in the wind farm. The proposed prediction methodology is based on Reservoir Computing and an over-sampling process for alleviating the high degree of unbalance in the dataset (non-ramp events are much more frequent than ramps). Three elements are combined in the prediction method: a recurrent neural network layer, a nonlinear kernel mapping and an ordinal logistic regression,to exploit the information provided by the order of the classes). Preprocessing is based on a variation of the standard synthetic minority over-sampling technique, which is applied to the reservoir activations (since the direct application over the input variables would damage its temporal structure). The performance of the method is analysed by comparing it against other state-of-the-art classifiers, such as Support Vector Machines, nominal logistic regression, an autoregressive ordinal neural network, or the use of leaky integrator neurons instead of the standard sigmoidal units. From the results obtained, the benefits of the kernel mapping and the ordinal model are clear, and, in general, the performance obtained with the Reservoir Computing approach is shown to be very robust in the detection of ramps.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ren21 (2017) Global status report, renewables. http://www.ren21.net/status-of-renewables/global-status-report/. Accessed Dec 2017
Cramer W, Yohe G (2013) Detection and attribution of observed impacts. IPCC5 work group 2, 5th assessment report, Chapter 18:1–94
Pryor SC, Barthelmie RJ (2010) Climate change impacts on wind energy: a review. Renew. Sustain. Energy Rev. 14:430–437
Salcedo-Sanz S, Pérez-Bellido ÁM, Ortiz-García EG, Portilla-Figueras A, Prieto L, Paredes D (2009) Hybridizing the fifth generation mesoscale model with artificial neural networks for short-term wind speed prediction. Renew. Energy 34(6):1451–1457
Díaz-Vico D, Torres-Barrán A, Omari A, Dorronsoro JR (2017) Deep neural networks for wind and solar energy prediction. Neural Process Lett 46:829–844
Wang J, Li Y (2017) Short-term wind speed prediction using signal preprocessing technique and evolutionary support vector regression. Neural Process Lett. Accessed Dec 2017
Cui M, Ke D, Sun Y, Gan D, Zhang J, Hodge BM (2015) Wind power ramp event forecasting using a stochastic scenario generation method. IEEE Trans Sustain Energy 6:422–433
Foley AM, Leahy PG, Marvuglia A, McKeogh EJ (2012) Current methods and advances in forecasting of wind power generation. Renew. Energy 37:1–8
Ouyang T, Zha X, Qin L (2013) A survey of wind power ramp forecasting. Energy Power Eng 5:368–372
Gallego-Castillo C, Cuerva-Tejero A, López-García O (2015) A review on the recent history of wind power ramp forecasting. Renew Sustain Energy Rev 52:1148–1157
Gallego-Castillo C, Costa A, Cuerva-Tejero A (2011) Improving short-term forecasting during ramp events by means of regime-switching artificial neural networks. Adv Sci Res 6:55–58
Zareipour H, Huang D, Rosehart W (2011) Wind power ramp events classification and forecasting: a data mining approach. In Proceedings of the IEEE power energy society general meeting, San Diego, CA, USA, pp 1–3
Bossavy A, Girard R, Kariniotakis G (2015) An edge model for the evaluation of wind power ramps characterization approaches. Wind Energy 18:1169–1184
Cornejo-Bueno L, Cuadra L, Jiménez-Fernández S, Acevedo-Rodríguez J, Prieto L, Salcedo-Sanz S (2017) Wind power ramp events prediction with hybrid machine learning regression techniques and reanalysis data. Energies 10(11):1–27
Cannon DJ, Brayshaw DJ, Methven J, Coker PJ, Lenaghan D (2015) Using reanalysis data to quantify extreme wind power generation statistics: a 33 years case study in Great Britain. Renew Energy 75:767–778
Gallego-Castillo C, García-Bustamante E, Cuerva-Tejero A, Navarro J (2015) Identifying wind power ramp causes from multivariate datasets: a methodological proposal and its application to reanalysis data. IET Renew Power Gener 9:867–875
Dorado-Moreno M, Cornejo-Bueno L, Gutiérrez PA, Prieto L, Hervás-Martínez C, Salcedo-Sanz S (2017) Robust estimation of wind power ramp events with reservoir computing. Renew Energy 111:428–437
Pérez-Ortiz M, Jiménez-Fernández S, Gutiérrez PA, Alexandre E, Hervás-Martínez C, Salcedo-Sanz S (2016) A review of classification problems and algorithms in renewable energy applications. Energies 9:1–27
Gutiérrez PA, Pérez-Ortiz M, Sánchez-Monedero J, Fernández-Navarro F, Hervás-Martínez C (2016) Ordinal regression methods: survey and experimental study. IEEE Trans Knowl Data Eng 28:127–146
Fernández-Navarro F (2017) A generalized logistic link function for cumulative link models in ordinal regression. Neural Process Lett 46:251–269
Pérez-Ortíz M, Fernández-Delgado M, Cernadas E, Domínguez-Petit R, Gutiérrez PA, Hervás-Martínez C (2016) On the use of nominal and ordinal classifiers for the discrimination of states of development in fish oocytes. Neural Process Lett 44:555–570
Fernández JC, Salcedo-Sanz S, Gutierrez PA, Alexandre-Cortizo E, Hervás C (2015) Significant wave height and energy flux range forecast with machine learning classifiers. Eng Appl Artif Intell 43:44–53
Gutiérrez PA, Salcedo-Sanz S, Hervás-Martínez C, Prieto L (2012) Ordinal and nominal classification of wind speed from synoptic pressure patterns. Eng Appl Artif Intell 26:1008–1015
Georgoulas G, Koliios S, Karvelis P, Stylios C (2016) Examining nominal and ordinal classifiers for forecasting wind speed. In: 2016 IEEE 8th international conference on intelligent systems, pp 504–509
Lukoševičius M, Jaeger H (2009) Reservoir computing approaches to recurrent neural network training. Comput Sci Rev 3(3):127–149
Verstraeten D, Schrauwen B, d’Haene M, Stroobandt D (2007) An experimental unification of reservoir computing methods. Neural Netw 20(3):391–403
Liu D, Wang J, Wang H (2015) Short-term wind speed forecasting based on spectral clustering and optimised echo state networks. Renew Energy 78:599–608
Ferreira AA, Ludermir TB, de Aquino RR, Lira MM, Neto ON (2008) Investigating the use of reservoir computing for forecasting the hourly wind speed in short-term. In: IEEE world congress on computational intelligence IJCNN 2008. IEEE international joint conference on neural networks, pp 1649–1656
Jaeger H (2001) The “echo state” approach to analysing and training recurrent neural networks. GMD report 148; German National Research Center for Information Technology, pp 1–43
Huang G, Zhu Q, Siew C (2006) Extreme learning machone: theory and applications. Neurocomputing 70:489–501
Dorado-Moreno M, Durán-Rosal AM, Guijo-Rubio D, Gutiérrez PA, Prieto L, Salcedo-Sanz S, Hervás-Martínez C (2016) Multiclass prediction of wind power ramp events combining reservoir computing and support vector machines. In: Conference of the Spanish Association for artificial intelligence, lecture notes in computer science, vol 9868, pp 300–309
Rahimi A, Recht B (2007) Random features for large-scale Kernel machines. Neural Inf Process Syst Adv Neural Inf Process Syst 20:1177–1184
Rennie JDM, Srebro N (2005) Loss functions for preference levels: regression with discrete ordered labels. In: Proceedings of the IJCAI multidisciplinary workshop on advances in preference handling, pp 180–186
Kotsiantis S, Kanellopoulos D, Pintelas P (2006) Handling imbalanced datasets: a review. GESTS Int Trans Comput Sci Eng 30:25–30
Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357
Luengo J, Fernández A, García S, Herrera F (2011) Addressing data complexity for imbalanced data sets: analysis of SMOTE-based oversampling and evolutionary undersampling. Soft Comput 15:1909–1936
Rodan A, Tiňo P (2011) Minimum complexity echo state network. IEEE Trans Neural Netw 22:131–144
Dee DP, Uppala SM, Simmons AJ, Berrisford P, Poli P (2011) The ERA-Interim reanalysis: configuration and performance of the data assimilation system. Quart J R Met Soc 137:553–597
Dorado-Moreno M, Cornejo-Bueno L, Gutiérrez PA, Prieto L, Salcedo-Sanz S, Hervás-Martínez C (2017) Combining reservoir computing and over-sampling for ordinal wind power ramp prediction. In: International work-conference on artificial neural networks, lecture notes in computer science, vol 10305, pp 708–719
Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77:802–813
McCullagh P (1980) Regression models for ordinal data. J R Stat Soc 42:109–142
Pedregosa F, Bach F, Gramfort A (2017) On the consistency of ordinal regression methods. J Mach Learn Res 18:1–35
Haixiang G, Yijing L, Shang J, Mingyun G, Yuanyue H, Bing G (2017) Learning from class-imbalanced data: review of methods and applications. Expert Syst Appl 73:220–239
Li J, Fong S, Sung Y, Cho K, Wong R, Wong KKL (2016) Adaptive swarm cluster-based dynamic multi-objective synthetic minority over-sampling technique algorithm for tackling binary imbalanced datasets in biomedical data classification. Biodata Min 9:37–52
Bach M, Werner A, Zywiec J, Pluskiewicz W (2017) The study of under- and over-sampling methods’ utility in analysis of highly imbalanced data on osteoporosis. Inf Sci 384:174–190
Baccianella S, Esuli A, Sebastiani F (2009) Evaluation measures for ordinal regression. In: Proceedings of the 9th international conference on intelligent systems design and applications, pp 283–287
Boser B, Guyon I, Vapnik V (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual ACM workshop on computational learning theory, Ed. Pittsburgh, pp 144–152
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
Hsu CW, Lin CJ (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Netw 13:415–425
Jaeger H, Lukoševičius M, Popovici D, Siewert U (2007) Optimization and applications of echo state networks with leaky-integrator neurons. Neural Netw 20(3):335–352
Huo F, Poo A (2013) Nonlinear autoregressive network with exogenous inputs based contour error reduction in CNC machines. Int J Mach Tools Manuf 67:45–52
Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J (2017) LSTM: a search space odyssey. IEEE Trans Neural Netw Learn Syst 28:2222–2232
Acknowledgements
This work has been subsidized by the TIN2017-85887-C2-1-P, TIN2017-85887-C2-2-P, TIN2017-90567-REDT, TIN2014-54583-C2-1-R and TIN2014-54583-C2-2-R projects of the Spanish Ministry of Economy and Competitiveness (MINECO) and FEDER funds. Manuel Dorado-Moreno’s research has been subsidised by the FPU Predoctoral Program (Spanish Ministry of Education and Science), grant reference FPU15/00647. The authors acknowledge NVIDIA Corporation for the grant of computational resources through the GPU Grant Program
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Dorado-Moreno, M., Gutiérrez, P.A., Cornejo-Bueno, L. et al. Ordinal Multi-class Architecture for Predicting Wind Power Ramp Events Based on Reservoir Computing. Neural Process Lett 52, 57–74 (2020). https://doi.org/10.1007/s11063-018-9922-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-018-9922-5