Artigo completo - Open Access.

Idioma principal | Segundo idioma

HYBRID MODEL OF WIND SPEED PREDICTION IN SHORT TIME RANGE USING WRF AND ARTIFICIAL NEURAL NETWORKS

MODELO HÍBRIDO DE PREVISÃO DE VELOCIDADE DO VENTO A CURTO PRAZO UTILIZANDO WRF E REDES NEURAIS ARTIFICIAIS

Teixeira, Rafael Silva ; Conterato, Flávio Santos ; Dias, Palmira Maria Acioli ; Kitagawa, Yasmin Kaore Lago; Moreira, Davidson Martins ; Nascimento, Erick Giovani Sperandio ;

Artigo completo:

This paper applies a hybrid model of wind speed forecasting in short-term to the watershed basin of Paranapanema, Brazil, as strategy to decrease computational demand typically observed in exclusively WRF-based predictions, while deals with an also common lack of measured atmospheric variables in greater spatial and time frame resolution. The model uses adjusted variables from real data simulated WRF outputs for the target area as input of a MultiLayer Perceptron (MLP) Neural Network (ANN) configured with Feed-forward Backpropagation algorithm, tested with different combinations of parameters. The association here proposed aims to match the best of both methods to mitigate each other’s typical issues and provide, supported by future works, even better accurate results also for other atmospheric elements.

Artigo completo:

O modelo híbrido aqui aplicado à bacia hidrográfica do Paranapanema, Brasil, sugere a diminuição da demanda computacional tipicamente observada em previsões baseadas exclusivamente em WRF; e lida com a também comum baixa oferta de dados atmosféricos em maior resolução espacial e temporal. Variáveis ajustadas, oriundas de simulações de dados reais no WRF para a área alvo, são utilizadas como dados de entrada de uma Rede Neural (RNA) MultiLayer Perceptron (MLP) com algoritmo Feed-forward Backpropagation (para diferentes combinações de parâmetros). Esta associação visa combinar o melhor dos dois métodos para mitigar os problemas típicos um do outro e fornecer, apoiado por trabalhos futuros, resultados ainda melhores e precisos também para outros elementos atmosféricos.

Palavras-chave: ANN; Artificial Intelligence; Atmospheric Science; MLP; WRF,

Palavras-chave: Ciência Atmosférica; Inteligência Artificial; MLP; RNA; WRF.,

DOI: 10.5151/siintec2020-HYBRIDMODEL

Referências bibliográficas
  • [1] 1 BARTHOLD L. et al. Improving flash flood forecasts: The HMT-WPC flash flood and intense rainfall experiment. Bull. Amer. Meteor. Soc., v. 96, p. 1859–1866, 2015. 2 S ARAÚJO, A. et al. Ciência, Tecnologia e Sociedade; Trabalho e Educação: possibilidades de integração no currículo da Educação Profissional Tecnológica. Rev. Ensaio Belo Horizonte, v. 14, n.1, p. 99-112, jan-abr, , 2012. 3 PENG, H et al. A hybrid strategy of short-term wind power prediction Renewable Energy v. 50, p. 590-595, 2013. 4 SKAMAROCK, W.C. et al. A Description of the Advanced Research WRF Version 3 (NCAR Technical Note), Mesoscale and Microscale Meteorology Division of NCAR. Boulder, Colorado, USA, 2008.5 KURTH, T. et al. Exascale deep learning for climate analytics. In Proceedings of the international conference for high performance computing, networking, storage, and analysis, IEEE Press, Dallas, Texas, p. 51, 2018. 6 LAGERQUIST, R. et al. Deep learning for spatially explicit prediction of synoptic-scale fronts. Weather and Forecasting, v. 34, n. 4, p. 1137–1160, 2019.7 CHENG, W.Y.Y. et al. Short-term wind forecast of a data assimilation/weather forecasting system with wind turbine anemometer measurement assimilation. Renewable Energy v. 107, p. 340-351, 2017.8 WASILEWSKIA, J. et al. Short-term electric energy production forecasting at wind power plants in pareto-optimality context. Renewable and Sustainable Energy Reviews v. 69, p. 177-187, 2017.9 LIU, H et al. Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short-term memory neural network and Elman neural network. Energy Conversion and Management, v. 156, 15 January, p. 498-514, 2018. 10 ZUCATELLI, P.J.et al. Short-term wind speed forecasting in Uruguay using computational intelligence. Heliyon, v. 5, Issue 5, May, e01664, 2019. 11 AKINCI, T.C. Short term wind speed forecasting with ANN in Batman, Turkey. Electron Electr Eng 1(107), p. 41–5., 201 12 NOGAY, H.S., et al. Application of artificial neural networks for short term wind speed forecasting in Mardin, Turkey. J. energy South. Afr. 23(4), p. 2-7, 2012.13 OKUMUS, I. et al. Current status of wind energy forecasting and a hybrid method for hourly predictions. Energy Conversion and Management, v 123, p. 362-371, 2016. 14 JUNIOR, A. et al. Assessing Recurrent and Convolutional Neural Networks for Tropospheric Ozone Forecasting in The Region of Vitória, Brazil, Air Polution, June p. 101-112, 2020.
Como citar:

Teixeira, Rafael Silva ; Conterato, Flávio Santos ; Dias, Palmira Maria Acioli ; Kitagawa, Yasmin Kaore Lago; Moreira, Davidson Martins ; Nascimento, Erick Giovani Sperandio ; "HYBRID MODEL OF WIND SPEED PREDICTION IN SHORT TIME RANGE USING WRF AND ARTIFICIAL NEURAL NETWORKS", p. 617-625 . In: Anais do VI Simpósio Internacional de Inovação e Tecnologia. São Paulo: Blucher, 2020.
ISSN 2357-7592, ISBN: 2357-7592
DOI 10.5151/siintec2020-HYBRIDMODEL

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações