Article - Open Access.

Idioma principal | Segundo idioma

PREVISÃO DA VELOCIDADE DO VENTO A CURTO PRAZO EM REGIÃO TROPICAL UTILIZANDO WAVELETS E INTELIGÊNCIA ARTIFICIAL

SHORT-TERM WIND SPEED FORECASTING IN TROPICAL REGION USING WAVELETS AND ARTIFICIAL INTELLIGENCE

Zucatelli, Pedro Junior ; Nascimento, Erick Giovani Sperandio ; Santos, Alex Álisson Bandeira ; Moreira, Davidson Martins ; , ;

Article:

Neste trabalho, é apresentado a previsão da velocidade do vento a curto prazo na região tropical de Mucuri, Bahia, Brasil, aplicando algoritmo de aprendizado de máquina supervisionado por meio da Rede Neural Multilayer Perceptron, Rede Neural Recorrente e Decomposição Wavelet, isto para a série temporal horária representativa deste local. Para treinar a Rede Neural Artificial (RNA) e validar a técnica, dados anemométricos de um mês foram coletados por uma torre anemométrica com altura de 100 m. Diferentes famílias de Wavelets e diferentes configurações de RNA foram aplicadas para este local e altura. Com base nos resultados alcançados, pode-se concluir que o método proposto (RNN + Meyer Wavelets) apresentou os melhores resultados no horizonte de previsão de curto prazo, isto é, 12 h à frente.

Article:

In this paper, the short-term wind speed forecasting in the tropical region of Mucuri, Bahia, Brazil, applying supervised machine learning algorithm by Multilayer Perceptron Neural Network, Recurrent Neural Network technique and Wavelet Packet Decomposition to the hourly time series representative of the site is presented. To train the Artificial Neural Network (ANN) and validate the technique, data for one month were collected by an anemometric tower at height of 100.0 m. Different Wavelet families and different ANN configurations were applied for this site and height. Based on the outcomes of the study cases and results, it can be concluded that the proposed method (RNN + Meyer Wavelets) performed the best results in short-term forecasting horizon (12 h ahead).

Palavras-chave: Ciência Atmosférica; Ciência Computacional; Energia,

Palavras-chave: Atmospheric Science; Computer Science; Energy,

DOI: 10.5151/siintec2019-46

Referências bibliográficas
  • [1] 1 CHENG, W.Y.Y., Liu, Y., Bourgeois, A.J., Wu, Y. and Haupt, S.E., 2017. Short-term wind forecast of a data assimilation/weather forecasting system with wind turbine anemometer measurement assimilation. Renewable Energy 107, 340-35
  • [2] 2 PENG, H., Liu, F. and Yang, X., 2013. A hybrid strategy of short-term wind power prediction. Renewable Energy 50, 590-595.
  • [3] 3 WASILEWSKIA, J. and Baczynski, D., 2017. Short-term electric energy production forecasting at wind power plants in pareto-optimality context. Renewable and Sustainable Energy Reviews 69, 177-187.
  • [4] 4 LIU, H., Mi, X., Li, Y., 2018. Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short-term memory neural network and Elman neural network. Hui Liu; Xi-wei Mi; Yan-fei Li. Energy Conversion and Management. Volume 156, 15 January 2018, Pages 498-51 2018.
  • [5] 5 ZUCATELLI, P.J., Nascimento, E.G.S., Aylas, G.Y.R., Souza, N.B.P., Kitagawa, Y.K.L., Santos, A.A.B., Arce, A.M.G., Moreira, D.M., 2019. Short-term wind speed forecasting in Uruguay using computational intelligence. Heliyon, Volume 5, Issue 5, May 2019, e01664.
  • [6] 6 HU, J., Wang, J., Xiao, L., 2017. A hybrid approach based on the Gaussian process with t-observation model for short-term wind speed forecasts. Renew Energy 2017; 114:670–85.
  • [7] 7 ZHANG, J., Wei, Y., Tan, Z., Wang, K., and Tian, W., 201 A Hybrid Method for Short-TermWind Speed Forecasting. Sustainability 9, 596.
  • [8] 8 ERDEM, E. and Shi, J., 2011. ARMA based approaches for forecasting the tuple of wind speed and direction. Appl. Energy 88, 1405–1414.
  • [9] 9 LIU, H.P., Shi, J. and Erdem, E., 2010. Prediction of wind speed time series using modified Taylor Kriging method. Energy 35, 4870–487
  • [10] 10 LI, G., Shi, J. and Zhou J., 2011. Bayesian adaptive combination of short-term wind speed forecasts from neural network models. Renew Energy, 36, 352 – 9.
  • [11] 11 AKINCI, T.C., 20 Short term wind speed forecasting with ANN in Batman, Turkey. Electron Electr Eng 1(107), 41–5.
  • [12] 12 NOGAY, H.S., Akinci, T.C. and Eidukeviciute, M., 20 Application of artificial neural networks for short term wind speed forecasting in Mardin, Turkey. J. energy South. Afr. 23(4), 2-7.
  • [13] 13 OKUMUS, I. and Dinler, S., 2016. Current status of wind energy forecasting and a hybrid method for hourly predictions. Energy Conversion and Management 123, 362-371.
  • [14] 14 LIU, D., Wang, J. and Wang, H. 2015. Short-term wind speed forecasting based on spectral clustering and optimized echo state networks. Renew Energy 78, 599–608.
  • [15] 15 HU, Q., Zhang, R. and Zhou, Y., 2016. Transfer learning for short-term wind speed prediction with deep neural networks. Renew Energy 85, 83–95.
  • [16] 16 QIN, S., Liu, F., Wang, J. and Song, Y., 2015. Interval forecasts of a novelty hybrid model for wind speeds. Energy 1, 8–
  • [17] 17 CERVONE, G., Clemente-Harding, L., Alessandrini, S. and Monache, L.D., 20 Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble. Renewable Energy 108, 274-286.
  • [18] 18 RUSSEL, S. and Norvig, P., 2010. Artificial Intelligence: A Modern Approach. Stuart J. Russell and Peter Norvig. Third Edition. Pearson Education, Inc., 1153p.
  • [19] 19 PELLETIER, F., Masson, C. and Tahan, A., 2016. Wind turbine power curve modelling using artificial neural network. Renewable Energy 89, 207-214.
  • [20] 20 HAYKIN, S., 1999. Neural Networks: A Comprehensive Foundation. Simon Haykin. Second Edition. Pearson Education Inc. Hamilton, Ontario, Canada, 823p.
  • [21] 21 MORI, H. and Umezawa, Y., 2009. Application of NBTree to Selection of Meteorological Variables in Wind Speed Prediction, transmission & Distribution Conference & Exposition: Asia and Pacific, Seoul, Korea, 2009.
  • [22] 22 SUN S, Qiao H, Wei Y, Wang S., 2017. A new dynamic integrated approach for wind speed forecasting. Appl Energy 2017;197(June):151–62.
  • [23] 23 TASCIKARAOGLU A, Uzunoglu M., 2014. A review of combined approaches for prediction of short-term wind speed and power. Renew Sustain Energy Rev 2014; 34:243–54.
  • [24] 24 SKAMAROCK, W.C., Klemp, J.B., Dudhia, J., Gill, D.O., Barker, D.M., Huang, X.Y., Wang, W. and Powers, J.G., 2008. A Description of the Advanced Research WRF Version 3 (NCAR Technical Note), Mesoscale and Microscale Meteorology Division do NCAR. Boulder, Colorado, USA
Como citar:

Zucatelli, Pedro Junior; Nascimento, Erick Giovani Sperandio; Santos, Alex Álisson Bandeira; Moreira, Davidson Martins; , ; "PREVISÃO DA VELOCIDADE DO VENTO A CURTO PRAZO EM REGIÃO TROPICAL UTILIZANDO WAVELETS E INTELIGÊNCIA ARTIFICIAL", p. 365-372 . In: Anais do V Simpósio Internacional de Inovação e Tecnologia. São Paulo: Blucher, 2019.
ISSN 2357-7592, DOI 10.5151/siintec2019-46

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações