Wind power prediction of CNN-LSTM network model based on unsupervised algorithm processing

Hongtao Shi; Mingren Guan; Maosheng Ding

doi:10.1117/12.2611130

14 October 2021 Wind power prediction of CNN-LSTM network model based on unsupervised algorithm processing

Hongtao Shi, Mingren Guan, Maosheng Ding

Proceedings Volume 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation; 119303R (2021) https://doi.org/10.1117/12.2611130
Event: International Conference on Mechanical Engineering, Measurement Control, and Instrumentation (MEMCI 2021), 2021, Guangzhou, China

Abstract

Wind power prediction is of great significance to the safe and stable operation of power systems and the optimal allocation of energy. Aiming at the huge amount of related data in wind power prediction, a wind power prediction model based on unsupervised algorithm-CNN-LSTM is proposed. Firstly, an unsupervised algorithm is used to preprocess wind power-related data, which solves the problems of large redundancy and slow convergence of training data in traditional forecasting model; therefore the algorithm can be applied to multi-dimensional and large-scale data; then, convolution cyclic neural network model uses convolution neural network to perform multi-layer convolution , and pool stacking calculation on wind power, wind speed, wind direction and other data to extract the characteristic map of wind power data, and takes the characteristic map information as the input information of long-term and short-term memory neural network. Finally, an example is to verify the proposed method.

Citation Download Citation

Hongtao Shi, Mingren Guan, and Maosheng Ding "Wind power prediction of CNN-LSTM network model based on unsupervised algorithm processing", Proc. SPIE 11930, International Conference on Mechanical Engineering, Measurement Control, and Instrumentation, 119303R (14 October 2021); https://doi.org/10.1117/12.2611130

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available