Art

J-GLOBAL ID：202002219288094250   Reference number：20A2182671

Wind Power Generation Prediction with Function of Overfitting Prevention

過学習防止機能付きLSTMを用いた風力発電出力予測法

Author (2)： OKURA SOICHIRO (明治大) ,  MORI HIROYUKI (明治大)
Material： 電気学会研究会資料
Issue： PE-20-052-109/PSE-20-057-114 電力技術研究会/電力系統技術研究会  Page： 7-12  Publication year： Sep. 24, 2020 
JST Material Number： Z0924B  Document type： Proceedings
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *wind power generation ,  *prediction technique ,  machine learning ,  neural network(biomodel) ,  overload ,  time series analysis ,  forecast ,  wind farm ,  neural network(network) ,  prevention
Semi thesaurus term： deep learning ,  *Long short term memory ,  overfitting ,  *output forecast ,  deep neural network ,  recurrent neural network ,  *過学習防止

JST classification (1)： Wind power generation  (NB03120Q)

Reference (19)：

• Z. Huang and Z.S. Chalabi: ′′Use of time-series analysis to model and forecast wind speed,′′ J. of Wind Eng. And Industrial Aerodynamics, Vol. 56, No. 2-3, pp.311-322 (1995-5)
• S. Rajagopalan and S. Santoso: ′′Wind power forecasting and error analysis using the autoregressive moving average modeling′′, IEEE PES 2009, 6 pages (2009)
• M. A. Mohandas, S. Rahman, and T. Halawani: ′′A neural networks approach for wind speed prediction′′, J. of Renewable Energy, vol. 13, pp.345-354 (1998).
• A. Steftos: ′′A novel approach for the forecasting of mean hourly wind speed time series′′, J. of Renewable Energy, vol.27, pp.163-174 (2002).
• H. Mori and E. Kutara: ′′Application of Gaussian Process to wind speed forecasting for wind power generation′′, Proc. of IEEE ICSET2008, pp. 956-959, Singapore (2008).

Terms in the title (4)： 過学習 ,  LSTM ,  風力発電 ,  出力予測