New Dimensionality Reduction Method of Wind Power Curve Based on Deep Learning

被引：0

作者：

Zhang, Yujing ^{[1
]}

Qiao, Ying ^{[1
]}

Lu, Zongxiang ^{[1
]}

Wang, Wei ^{[2
]}

机构：

[1] Tsinghua Univ, State Key Lab Control & Simulat Power Syst & Gene, Dept Elect Engn, Beijing, Peoples R China

[2] State Grid GanSu Elect Power Co, Lanzhou, Gansu, Peoples R China

来源：

2018 INTERNATIONAL CONFERENCE ON POWER SYSTEM TECHNOLOGY (POWERCON) | 2018年

关键词：

Deep Learning; Convolutional Autoencoder; Dimensionality Reduction; Wind power curve;

D O I：

暂无

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

Wind power curve is a key tool to characterize wind power output feature, and is also the basis of wind power planning and operation research. The wind power curve is a high dimension matric data with local property. So it's a vital task to find an effective method to reduce dimension of the curve. In this paper, the latest techniques of artificial intelligence and deep learning are introduced to probe a new method for reducing the dimension of wind power curve. The convolutional autoencoder of typical deep learning framework is redesigned, and it learns feature representation from massive history data. The experiment result shows that the proposed autoencoder is better fit the wind power curve dimensionality reduction study.

引用

页码：4357 / 4361

页数：5

共 50 条

[1] Hyperspectral image classification based on manifold spectral dimensionality reduction and deep learning method
Shi, Yun
Ma, Donghui
Lyu, Jie
Li, Jie
Shi, Jingjian
[J]. Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2020, 36 (06): : 151 - 160
[2] WIND POWER PREDICTION BASED ON DEEP LEARNING METHOD AND ITS UNCERTAINTY
Yubo, T.
Hongkun, C.
Jie, W.
Qian, H.
Ruixi, Y.
[J]. JOURNAL OF THE BALKAN TRIBOLOGICAL ASSOCIATION, 2015, 21 (4A): : 1166 - 1174
[3] Wind Power Prediction and Pattern Feature Based on Deep Learning Method
Tao, Yubo
Chen, Hongkun
Qiu, Chuang
[J]. 2014 IEEE PES ASIA-PACIFIC POWER AND ENERGY ENGINEERING CONFERENCE (IEEE PES APPEEC), 2014,
[4] A New Dimensionality Reduction Method with Correlation Analysis and Universum Learning
Chen X.
Wang L.
[J]. Pattern Recognition and Image Analysis, 2018, 28 (2) : 174 - 184
[5] A VAE-Bayesian deep learning scheme for solar power generation forecasting based on dimensionality reduction
Kaur, Devinder
Islam, Shama Naz
Mahmud, Md. Apel
Haque, Md. Enamul
Anwar, Adnan
[J]. ENERGY AND AI, 2023, 14
[6] Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures
Yashar Kiarashinejad
Sajjad Abdollahramezani
Ali Adibi
[J]. npj Computational Materials, 6
[7] Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures
Kiarashinejad, Yashar
Abdollahramezani, Sajjad
Adibi, Ali
[J]. NPJ COMPUTATIONAL MATERIALS, 2020, 6 (01)
[8] Short-term Power Forecasting Model Based on Dimensionality Reduction and Deep Learning Techniques for Smart Grid
Syed, Dabeeruddin
Refaat, Shady S.
Abu-Rub, Haitham
Bouhali, Othmane
[J]. 2020 IEEE KANSAS POWER AND ENERGY CONFERENCE (KPEC), 2020,
[9] Wind Turbine Power Curve Drawing based on Method of Grid
Li, Hangtao
[J]. PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, : 3896 - 3899
[10] Wind power forecasting based on hybrid CEEMDAN-EWT deep learning method
Karijadi, Irene
Chou, Shuo-Yan
Dewabharata, Anindhita
[J]. RENEWABLE ENERGY, 2023, 218

← 1 2 3 4 5 →