Advertisement

A Broad Learning System with Ensemble and Classification Methods for Multi-step-ahead Wind Speed Prediction

  • Lingzi Zhu
  • Cheng LianEmail author
  • Zhigang Zeng
  • Yixin Su
Article
  • 45 Downloads

Abstract

Short-term wind speed prediction plays a significant role in the management of large-scale wind power plants. However, wind speed prediction is extremely complex and difficult due to the volatility and non-linearity of wind. For this purpose, a broad learning system (BLS) with ensemble and classification named BLS-EC is proposed to predict multi-step-ahead wind speed. The proposed method is based on a new neural network termed the BLS, which could work out the complex non-linear relation by learning model while ensuring the computational efficiency. To overcome the randomness and instability of a single BLS, this paper proposes the BLS ensemble method to improve the generalization and stability of the network. In order to improve the accuracy of prediction, a method called classification-guided regression is proposed to distinguish different variation patterns of initial predicted wind speed. According to the classification result, different pattern sequences are re-predicted to obtain the final prediction result. Applying this thinking and method into research of three real-time wind speed datasets which were taken from Sotavento Galicia SA (SG), Alberta (ALB), and Newfoundland (NFL), the validity and practical value of this method can be demonstrated. Results obtained clearly show that BLS is better than existing methods ARIMA and RBF. Moreover, the BLS-EC method improved generalization performance and the predicting precision of a single BLS. In this study, the BLS-EC was proposed and successfully applied to wind speed prediction.

Keywords

Broad learning system Time series prediction Ensemble Classification-guided regression 

Notes

Funding Information

The work was financially supported by the National Key R&D Program of China under Grant 2017YFC1501301; the Natural Science Foundation of China under Grants 61876219, 61503144, 61673188, and 61761130081; the Excellent Dissertation Cultivation Funds of Wuhan University of Technology (2018-YS-066); and the Natural Science Foundation of Hubei Province of China under Grant 2017CFB519.

Compliance with Ethical Standards

Conflict of Interest

The authors declare that they have no conflicts of interest.

Ethical Approval

This article does not contain any studies with human participants or animals performed by any of the authors.

References

  1. 1.
    Khosravi A, Koury RNN, Machado L. Thermo-economic analysis and sizing of the components of an ejector expansion refrigeration system. Int J Refrig 2018;86:463–479.CrossRefGoogle Scholar
  2. 2.
    Song J, Wang J, Lu H. A novel combined model based on advanced optimization algorithm for short-term wind speed forecasting. Appl Energy 2018;215:643–658.CrossRefGoogle Scholar
  3. 3.
    Khosravi A, Koury RNN, Machado L, Pabon JJG. Energy, exergy and economic analysis of a hybrid renewable energy with hydrogen storage system. Energy. 2018;148:1087–1102.CrossRefGoogle Scholar
  4. 4.
    Zuluaga CD, Alvarez MA, Giraldo E. Short-term wind speed prediction based on robust Kalman filtering: an experimental comparison. Appl Energy 2015;156:321–330.CrossRefGoogle Scholar
  5. 5.
    El-Fouly THM, El-Saadany EF, Salama MMA. A study of wind farms output power prediction techniques. Proceedings north american power symposium; 2004. p. 249–254.Google Scholar
  6. 6.
    Lei M, Shiyan L, Chuanwen J, Hongling L, Yan Z. A review on the forecasting of wind speed and generated power. Renew Sustain Energy Rev 2009;13(4):915–920.CrossRefGoogle Scholar
  7. 7.
    Kusiak A, Zheng H, Song Z. Wind farm power prediction: a data-mining approach. Wind Energy 2009; 12(3):275–293.CrossRefGoogle Scholar
  8. 8.
    Kuik GV, Ummels B, Hendriks R. Sustainable energy technologies. Amsterdam: Springer; 2007.Google Scholar
  9. 9.
    Huang Z, Chalabi ZS. Use of time-series analysis to model and forecast wind speed. J Wind Eng Ind Aerodyn 1995;56:311–322.CrossRefGoogle Scholar
  10. 10.
    Kamal J, Jafri YZ. Time series models to simulate and forecast hourly averaged wind speed in Quetta. Sol Energy 1997;61:23–32.CrossRefGoogle Scholar
  11. 11.
    Sfetsos A. A comparison of various forecasting techniques applied to mean hourly wind speed time series. Renew Energy 2000;21:23–35.CrossRefGoogle Scholar
  12. 12.
    More A, Deo DC. Forecasting wind with neural networks. Marine Struct 2003;16(1):35–49.CrossRefGoogle Scholar
  13. 13.
    Thordarson FO. Conditional weighted combination of wind power forecasts. Wind Energy 2011;13(8):751–63.CrossRefGoogle Scholar
  14. 14.
    Giorgi MGD. Error analysis of short term wind power prediction models. Appl Energy 2011;88(4):1298–1311.CrossRefGoogle Scholar
  15. 15.
    Ranganayaki V, Deepa SN. Linear and non-linear proximal support vector machine classifiers for wind speed prediction. Cluster Comput 2019;22:5379–5390.CrossRefGoogle Scholar
  16. 16.
    Costa M, Pasero E. Artificial neural systems for verglass forecast. International joint conference on neural networks; 2001. p. 258–262.Google Scholar
  17. 17.
    Alexiadis MC, Dokopoulos PS, Sahsamanoglou HS, Manousaridis IM. Short-term forecasting of wind speed and related electric power. Sol Energy 1998;63(1):61–68.CrossRefGoogle Scholar
  18. 18.
    Li S, Wunsch DC, Hair EO, Giesselmann MG. Neural network for wind power generation with compressing function. International conference on neural networks; 1997. p. 115–120.Google Scholar
  19. 19.
    Damoisis IG, Alexiadis MC, Theocharis JB, Dokopoulos PS. A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation. IEEE Trans Energy Convers 2004;19(2):352–361.CrossRefGoogle Scholar
  20. 20.
    Katsigiannis YA, Tsikalakis AG, Georgilakis PS, Hatziargyriou ND. Improved wind power forecasting using a combined neuro-fuzzy and artificial neural network model. Advances in artificial intelligence, 4th Helenic conference on AI, SETN 2006, Heraklion, Crete, Greece, May 18-20; 2006. p. 105–115.CrossRefGoogle Scholar
  21. 21.
    Hu QH, Su PY, Yu DR, Liu JF. Pattern-based wind speed prediction based on generalized principal component analysis. IEEE Trans Sustain Energ 2014;5(3):866–874.CrossRefGoogle Scholar
  22. 22.
    Li Y, Yang P, Wang HJ. 2018. Short-term wind speed forecasting based on improved ant colony algorithm for LSSVM. Cluster Comput.  https://doi.org/10.1007/s10586-017-1422-2.CrossRefGoogle Scholar
  23. 23.
    Chen CLP, Liu ZL. Broad learning system: an effective and efficient incremental learning system without the need for deep architecture. IEEE Trans Neural Netw Learn Syst 2018;29(1):10–24.CrossRefGoogle Scholar
  24. 24.
    Chevillon G. Direct multi-step estimation and forecasting. J Econ Surveys 2001;21:746–785.CrossRefGoogle Scholar
  25. 25.
    Cox DR. Prediction by exponentially weighted moving averages and related methods. J R Stat Soc B 1961;23: 414–422.Google Scholar
  26. 26.
    Bontempi G. Long term time series prediction with multi-input multi-output local learning. Second European symposium on time series prediction 2008; 2008. p. 145–154.Google Scholar
  27. 27.
    Xu M, Han M, Chen CLP, Qiu T. 2018. Recurrent broad learning systems for time series prediction. IEEE Trans Cybern.  https://doi.org/10.1109/TCYB.2018.2863020.
  28. 28.
    Han M, Feng S, Chen CLP, Xu M, Qiu T. 2018. Structured manifold broad learning system: a manifold perspective for large-scale chaotic time series analysis and prediction. IEEE Trans Knowl Data Eng.  https://doi.org/10.1109/TKDE.2018.2866149.CrossRefGoogle Scholar
  29. 29.
    Hansen LK, Salamon P. Neural network ensembles. IEEE Trans Pattern Analy Mach Intell 1990;12(10): 993–1001.CrossRefGoogle Scholar
  30. 30.
    Liu N, Sakamoto JT, Cao J, Koh ZX, Ho AFW, Lin ZP, Ong MEH. Ensemble-based risk scoring with extreme learning machine for prediction of adverse cardiac events. Cogn Comput 2017;9:545–554.CrossRefGoogle Scholar
  31. 31.
    Dietterich T. An experimental comparison of three methods for constructing ensembles of decision trees: Bagging, boosting, and randomization. Mach Learn 2000;40(2):139–157.CrossRefGoogle Scholar
  32. 32.
    Menke W, Menke J. Patterns suggested by data, Environmental data analysis with Matlab, 2nd ed. Cambridge: Academic Press; 2016, pp. 165–185.Google Scholar
  33. 33.
    Uhlmann E, Pontes RP, Laghmouchi A, Bergmann A. Intelligent pattern recognition of a SLM machine process and sensor data. Procedia CIRP 2017;464-469:62.Google Scholar
  34. 34.
    Theodoridis S, Koutroumbas K. Chapter 1-Introduction. Pattern Recog, 4th ed. Cambridge: Academic Press; 2009, pp. 1–12.Google Scholar
  35. 35.
    Jain AK. Data clustering: 50 years beyond k-means. Pattern Recog Lett 2010;31(8):651–666.CrossRefGoogle Scholar
  36. 36.
    Huang G-B, Zhu Q-Y, Siew C-K2. Extreme learning machine: theory and applications. Neurocomputing 2006;70(1-3):489–501.CrossRefGoogle Scholar
  37. 37.
    Guo T, Zhang L, Tan XH. Neuron pruning-based discriminative extreme learning machine for pattern classification. Cogn Comput 2017;9:581–595.CrossRefGoogle Scholar
  38. 38.
    Savitha R, Suresh S, Kim HJ. A meta-cognitive learning algorithm for an extreme learning machine classifier. Cogn Comput 2014;6:253–263.CrossRefGoogle Scholar
  39. 39.
    Li N, Yu Y, Zhou ZH. Diversity regularized ensemble pruning. ECML PKDD’12; 2012. p. 330–345.Google Scholar
  40. 40.
    Wang F, Mi Z, Su S, Zhao H. Short-term solar irradiance forecasting model based on artificial neural network using statistical feature parameters. Energies. 2012;5:1355–1370.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Lingzi Zhu
    • 1
  • Cheng Lian
    • 1
    Email author
  • Zhigang Zeng
    • 2
  • Yixin Su
    • 1
  1. 1.School of AutomationWuhan University of TechnologyWuhanChina
  2. 2.School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina

Personalised recommendations