Open AccessWind power forecast based on convolutional neural network with multi-feature fusion
Author(s) -
Qiyue Huang,
Hao Wang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1684/1/012134
Subject(s) - wind power , computer science , randomness , convolutional neural network , artificial neural network , feature (linguistics) , reliability (semiconductor) , power (physics) , waveform , renewable energy , artificial intelligence , engineering , telecommunications , radar , electrical engineering , mathematics , linguistics , statistics , philosophy , physics , quantum mechanics
As a renewable clean energy, wind energy has the characteristics of large storage and wide distribution. It is one of the important components of energy internet. However, its strong fluctuation, randomness and discontinuity affect the stable operation of power system. To reduce the impact of wind power on power network and improve the reliability of power prediction, a wind power forecast method based on convolutional neural network with multi-feature fusion is proposed. Firstly, the wind power is classified according to the change characteristic of the waveform. The feature of the wind power waveform is extracted by the convolution neural network (CNN). Then, a prediction model based on multi-feature fusion algorithm is established to accurately predict wind power. Finally, the corresponding simulation model is established to verify that the proposed method can effectively improve the reliability of wind power prediction.