Skip to main content
Springer Nature Link
Log in

A Data Distribution-Based Ensemble Generation Applied to Wind Speed Forecasting

  • Conference paper
  • First Online:
Intelligent Systems (BRACIS 2024)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 15412))

Included in the following conference series:

  • 2 Accesses

Abstract

Variability in wind intensity and direction causes unstable electricity supply to the power system, making integrating this energy into the electrical system a significant challenge for operations and planning practices. Ensembles can be used as an alternative to address the complex patterns over time in wind speed time series. The appropriate size of the training partition for ensemble models depends on dataset characteristics. And, to enhance model training efficiency, it is important to minimize repetitive data. By maintaining a concise training set, it becomes easier to meet the requirements of software and hardware constraints. Mainly because, there is a growing interest in deploying machine learning models on edge devices. For these reasons, a new method called Local Distribution (LocDist) has been introduced in this paper to predict wind speed, utilizing local pattern recognition based on data distribution. In testing with three wind speed time series, LocDist created a compact training subset with less than 20% of the training data. The Diebold-Mariano hypothesis test was employed to assess the significance of the forecast errors of the proposal compared to individual and bagging methods that use the entire training set. The LocDist method with long short-term memory (LSTM) and gated recurrent unit (GRU) won in 100% of the cases. Additionally, the LocDist with extreme learning machines (ELM) and autoregressive integrated moving average (ARIMA) won or tied in 83% and 66% of the cases, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. GWE Council: GWEC\(|\) global wind report 2021. Global Wind Energy Council, Brussels, Belgium (2019)

    Google Scholar 

  2. GWE Council: GWEC\(|\) global wind report 2023. Global Wind Energy Council, Brussels, Belgium (2023)

    Google Scholar 

  3. A. B. d. E. E. ABEEólica, “Abeeólica \(|\) infovento,” INFOVENTO 31, 15 de junho de 2023 (2023)

    Google Scholar 

  4. Qu, Z., Mao, W., Zhang, K., Zhang, W., Li, Z.: Multi-step wind speed forecasting based on a hybrid decomposition technique and an improved back-propagation neural network. Renew. Energy 133, 919–929 (2019)

    Article  MATH  Google Scholar 

  5. Jiang, P., Wang, B., Li, H., Lu, H.: Modeling for chaotic time series based on linear and nonlinear framework: application to wind speed forecasting. Energy 173, 468–482 (2019)

    Article  MATH  Google Scholar 

  6. Ahmadi, M., Khashei, M.: Current status of hybrid structures in wind forecasting. Eng. Appl. Artif. Intell. 99, 104133 (2021)

    Article  MATH  Google Scholar 

  7. Mohandes, M.A., Halawani, T.O., Rehman, S., Hussain, A.A.: Support vector machines for wind speed prediction. Renew. Energy 29(6), 939–947 (2004)

    Article  MATH  Google Scholar 

  8. Salcedo-Sanz, S., Ortiz-Garcı, E.G., Pérez-Bellido, Á.M., Portilla-Figueras, A., Prieto, L., et al.: Short term wind speed prediction based on evolutionary support vector regression algorithms. Exp. Syst. Appl. 38(4), 4052–4057 (2011)

    Article  MATH  Google Scholar 

  9. Kong, X., Liu, X., Shi, R., Lee, K.Y.: Wind speed prediction using reduced support vector machines with feature selection. Neurocomputing 169, 449–456 (2015)

    Article  MATH  Google Scholar 

  10. Saavedra-Moreno, B., Salcedo-Sanz, S., Carro-Calvo, L., Gascón-Moreno, J., Jiménez-Fernández, S., Prieto, L.: Very fast training neural-computation techniques for real measure-correlate-predict wind operations in wind farms. J. Wind Eng. Ind. Aerodyn. 116, 49–60 (2013)

    Article  MATH  Google Scholar 

  11. Memarzadeh, G., Keynia, F.: A new short-term wind speed forecasting method based on fine-tuned LSTM neural network and optimal input sets. Energy Convers. Manage. 213, 112824 (2020)

    Article  MATH  Google Scholar 

  12. Liu, X., Lin, Z., Feng, Z.: Short-term offshore wind speed forecast by seasonal ARIMA - a comparison against GRU and LSTM. Energy 227, 120492 (2021)

    Article  Google Scholar 

  13. Ferreira, M., Santos, A., Lucio, P.: Short-term forecast of wind speed through mathematical models. Energy Rep. 5, 1172–1184 (2019)

    Article  MATH  Google Scholar 

  14. Wu, J., Li, N.: Impact of components number selection in truncated gaussian mixture model and interval partition on wind speed probability distribution estimation. Sci. Total Environ. 883, 163709 (2023)

    Article  Google Scholar 

  15. Robinson, P.: Analysis of time series from mixed distributions. Ann. Stat., 915–925 (1982)

    Google Scholar 

  16. Santos Júnior, D.S.O., de Mattos Neto, P.S.G., de Oliveira, J.F.L., Cavalcanti, G.D.C.: A hybrid system based on ensemble learning to model residuals for time series forecasting. Inf. Sci. 649, 119614 (2023)

    Google Scholar 

  17. de Mattos Neto, P.S., Cavalcanti, G.D., Firmino, P.R., Silva, E.G., Nova Filho, S.R.V.: A temporal-window framework for modelling and forecasting time series. Knowl. Based Syst. 193, 105476 (2020)

    Google Scholar 

  18. Petropoulos, F., Hyndman, R.J., Bergmeir, C.: Exploring the sources of uncertainty: why does bagging for time series forecasting work? Eur. J. Oper. Res. 268(2), 545–554 (2018)

    Article  MATH  Google Scholar 

  19. Bergmeir, C., Hyndman, R.J., Benítez, J.M.: Bagging exponential smoothing methods using STL decomposition and Box-Cox transformation. Int. J. Forecast. 32(2), 303–312 (2016)

    Article  MATH  Google Scholar 

  20. Sergio, A.T., de Lima, T.P., Ludermir, T.B.: Dynamic selection of forecast combiners. Neurocomputing 218, 37–50 (2016)

    Article  MATH  Google Scholar 

  21. Hu, J., Wang, J., Zeng, G.: A hybrid forecasting approach applied to wind speed time series. Renew. Energy 60, 185–194 (2013)

    Article  MATH  Google Scholar 

  22. Ruiz-Aguilar, J.J., Turias, I., González-Enrique, J., Urda, D., Elizondo, D.: A permutation entropy-based EMD-ANN forecasting ensemble approach for wind speed prediction. Neural Comput. Appl. 33(7), 2369–2391 (2021)

    Article  MATH  Google Scholar 

  23. Jiang, Z., Che, J., Wang, L.: Ultra-short-term wind speed forecasting based on EMD-VAR model and spatial correlation. Energy Convers. Manage. 250, 114919 (2021)

    Article  MATH  Google Scholar 

  24. Bowden, G.J., Maier, H.R., Dandy, G.C.: Optimal division of data for neural network models in water resources applications. Water Resour. Res. 38(2), 2–1 (2002)

    Article  MATH  Google Scholar 

  25. Deng, L., Li, G., Han, S., Shi, L., Xie, Y.: Model compression and hardware acceleration for neural networks: a comprehensive survey. Proc. IEEE 108(4), 485–532 (2020)

    Article  MATH  Google Scholar 

  26. Ribeiro, R., Fanzeres, B.: Identifying representative days of solar irradiance and wind speed in Brazil using machine learning techniques. Energy AI 15, 100320 (2024)

    Article  MATH  Google Scholar 

  27. Torres, J.L., Garcia, A., De Blas, M., De Francisco, A.: Forecast of hourly average wind speed with ARMA models in Navarre (Spain). Sol. Energy 79(1), 65–77 (2005)

    Article  MATH  Google Scholar 

  28. Tetko, I.V., Villa, A.E.: Efficient partition of learning data sets for neural network training. Neural Netw. 10(8), 1361–1374 (1997)

    Article  MATH  Google Scholar 

  29. Hodges, J., Jr.: The significance probability of the Smirnov two-sample test. Ark. Mat. 3(5), 469–486 (1958)

    Article  MathSciNet  MATH  Google Scholar 

  30. INPE: Rede do sistema de organização nacional de dados ambientais (2020). http://sonda.ccst.inpe.br/index.html. Accessed 27 Jul 2023

  31. Cerqueira, V., Torgo, L., Soares, C.: A case study comparing machine learning with statistical methods for time series forecasting: size matters. J. Intell. Inf. Syst. 59(2), 415–433 (2022)

    Article  MATH  Google Scholar 

  32. Andrawis, R.R., Atiya, A.F., El-Shishiny, H.: Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition. Int. J. Forecast. 27(3), 672–688 (2011)

    Article  MATH  Google Scholar 

  33. Hyndman, R.J., et al.: “Package ‘forecast’,” Online (2024). https://cran.r-project.org/web/packages/forecast/forecast.pdf

  34. Meyer, D., et al.: e1071: Misc functions of the department of statistics, probability theory group (formerly: E1071), TU Wien. R package version (2023)

    Google Scholar 

  35. Mouselimis, L., Gosso, A., Jonge, E.: elmNNRcpp: the extreme learning machine algorithm. R package (2023)

    Google Scholar 

  36. Chollet, F.: et al. “Keras” (2015). https://keras.io

  37. Diebold, F.X., Mariano, R.S.: Comparing predictive accuracy. J. Bus. Econ. Stat. 13(3) (1995)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Centro de Informática (CIn), Universidade Federal de Pernambuco (UFPE), Recife, PE, Brazil

    Diogo M. Almeida, Paulo S. G. de Mattos Neto & Daniel C. Cunha

Authors
  1. Diogo M. Almeida
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Paulo S. G. de Mattos Neto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daniel C. Cunha
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Diogo M. Almeida .

Editor information

Editors and Affiliations

  1. Universidade Federal Fluminense, Niterói, Brazil

    Aline Paes

  2. Instituto Tecnológico de Aeronáutica, São José dos Campos, Brazil

    Filipe A. N. Verri

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Almeida, D.M., de Mattos Neto, P.S.G., Cunha, D.C. (2025). A Data Distribution-Based Ensemble Generation Applied to Wind Speed Forecasting. In: Paes, A., Verri, F.A.N. (eds) Intelligent Systems. BRACIS 2024. Lecture Notes in Computer Science(), vol 15412. Springer, Cham. https://doi.org/10.1007/978-3-031-79029-4_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-79029-4_2

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-79028-7

  • Online ISBN: 978-3-031-79029-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics