PREDICTION MODEL OF WIND SPEED AND DIRECTION USING DEEP NEURAL NETWORK

Anggraini Puspita Sari, Hiroshi Suzuki, Takahiro Kitajima, Takashi Yasuno, Dwi Arman Prasetya

Abstract


This paper presents the prediction system of wind speed and direction using a feed-forward backpropagation neural network (FFBPNN).  The input of the prediction system is wind speed and direction which are numerical data and provided by Automated Meteorological Data Acquisition System (AMeDAS) in Japan. The performances of the proposed system is evaluated based on mean square error (MSE) between predicted and observed data. In this paper, we substantiate the usefulness of the proposed prediction system improving prediction accuracy compared to four prediction models.

Keywords


feed-forward, backpropagation, neural network, wind speed, wind direction.

Full Text:

PDF

References


N. L. Panwar, S. C. Kaushik, and S. Kothari, “Role of renewable energy sources in environmental protection: A review,” Renew. Sustain. Energy Rev., vol. 15, no. 3, pp. 1513-1524, 2011.

Hitoshi Sori and Takashi Yasuno, “Several Hours Ahead Wind Speed Prediction System Using Correction Recurrent Neural Network,” Proc. International Workshop on Nonlinear Circuits, Communications and Signal Processing (NSCP ’09), 2009, pp. 621-624.

Y. Miyabe, T. Kitajima, and T. Yasuno, “Wind Speed Prediction Model Using Neural Networks Classified By Observed Wind Speed,” Proc RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NSCP 2015), 2015, pp. 230-233.

A. Aguinaga, X. Luo, V. Hidalgo, E. Cando, and F. Llulluna, “A feed-forward backpropagation neural network method for remaining useful life prediction of Francis turbines,” Proc. World Congr. Mech. Chem. Mater. Eng., no. 126, 2017.

A.P. Sari, H. Suzuki, R. Fukuoka, T. Kitajima, and T.Yasuno “Prediction Model of Wind Speed and Direction using Convolutional Neural Network,” Proc. SICE Shikoku Conference, 2019, vol. 2, pp. 23-26.

R. E. Neapolitan and R. E. Neapolitan, Neural Networks and Deep Learning, Yorktown Heights, NY: Springer, 2018, pp. 19-47.

S. Samarasinghe, “Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition,” United States: Auerbach, 2007, pp. 73-109.




DOI: https://doi.org/10.26905/jeemecs.v3i1.3946

Refbacks

  • There are currently no refbacks.




JEEMECS (Journal of Electrical Engineering, Mechatronic and Computer Science)
Electrical Engineering Department, Faculty of Engineering



Mailling Address:

  • Address: Taman Agung Street No. 1, Sukun, Malang City, East Java, 65146, Indonesia.
  • Website: http://jurnal.unmer.ac.id/index.php/jeemecs/
  • Phone: +62 856 - 4850 - 9998 
  • Email: [email protected]


JEEMECS (Journal of Electrical Engineering, Mechatronic and Computer Science) is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License Creative Commons License

Copyright ©2020 University of Merdeka Malang Powered by Open Journal Systems.