Short-Term Wind Speed Prediction based on Deep Learning

2018 International Conference on Construction, Aviation and Environmental Engineering

生态环境科学;生物科学

Chu, Jingchun^1^2 ; Yuan, Ling^1^2 ; Wang, Wenliang^1^2 ; Pan, Lei^1^2 ; Wei, Jie^1

Guodian United Power Technology Company Ltd, Beijing

100039, China^1

Wind Power Equipment and Control State Key Laboratory, Baoding Hebei

071000, China^2

关键词: Fuzzy rough set theory;    Generalization ability;    Learning abilities;    Prediction accuracy;    Short-term wind speed predictions;    Spatial characteristics;    Stable operation;    Wind speed forecasting;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/233/5/052007/pdf
DOI  :  10.1088/1755-1315/233/5/052007

来源: IOP

【 摘 要 】

Wind speed forecasting has great significance to the improvement of wind turbine intelligent control technology and the stable operation of power system. In this paper, the Long Short-term Memory (LSTM) mode with deep learning ability combined with the fuzzy-rough set theory has been proposed to do short-term wind speed prediction. Fuzzy rough sets can reduce input and spatial characteristics. The main factors affecting wind speed were found as input of the prediction model of LSTM neural network. Deep learning conforms to the trend of big data. It has strong generalization ability on massive data learning. The experimental results show that the Fuzzy rough set Long Short-term Memory (FRS-LSTM) model has higher prediction accuracy than traditional neural network.