DocumentCode :
2601188
Title :
Direct multi-step prediction of wind speed based on chaos analysis and DRNN
Author :
Xingjie, Liu ; Yanqing, Zhang ; Zengqiang, Mi ; Xiaowei, Fan ; Junhua, Wu
Author_Institution :
Dept. of Electr. Eng., North China Electr. Power Univ., Baoding, China
fYear :
2009
fDate :
6-7 April 2009
Firstpage :
1
Lastpage :
5
Abstract :
The direct multi-step prediction employs measurement data but not the results of single-step prediction. So it should have a better prediction effect for short-term wind speed. Aiming to the chaotic nature of wind speed data, a novel direct multi-step prediction approach for wind speed has been presented in this paper. This approach was based on chaos analysis and dynamic recurrent neural network(DRNN). According to the phase space reconstruction theory, the phase space of wind speed data was first reconstructed. As a result, the attractor reflecting the inner rules of wind speed data was obtained. Then a DRNN model was established on the basis of the attractor. After training the network, the built model was used to directly predict the wind speed ahead of some steps. The detailed procedures were introduced in this paper. The results of a wind farm´s simulation show that the proposed approach greatly improves the multi-step prediction accuracy.
Keywords :
chaos; neural nets; power engineering computing; wind power; DRNN; chaos analysis; dynamic recurrent neural network; phase space reconstruction theory; wind farm; wind speed direct multistep prediction; Accuracy; Chaos; Neural networks; Power system reliability; Prediction methods; Predictive models; Recurrent neural networks; Wind energy; Wind farms; Wind speed; chaos analysis; direct multi-step prediction; dynamic recurrent neural network(DRNN); wind farm; wind speed;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Sustainable Power Generation and Supply, 2009. SUPERGEN '09. International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4934-7
Type :
conf
DOI :
10.1109/SUPERGEN.2009.5348114
Filename :
5348114
Link To Document :
بازگشت