DocumentCode :
2942434
Title :
The Research of Daily Total Solar-Radiation and Prediction Method of Photovoltaic Generation Based on Wavelet-Neural Network
Author :
Zhou, Hong ; Sun, Wentao ; Liu, Dichen ; Zhao, Jie ; Yang, Nan
Author_Institution :
Sch. of Electr. Eng., Wuhan Univ., Wuhan, China
fYear :
2011
fDate :
25-28 March 2011
Firstpage :
1
Lastpage :
5
Abstract :
Solar energy is developing fast recently. Solar energy has the feature of intermittent, fluctuation and random, and it has serious harms on large scale photovoltaic grid-connected generation. This paper proposes a method to predict daily total solar-radiation and photovoltaic generation using wavelet-neural network. This method uses wavelet function to substitute the transfer function of neural-network hidden layer. In the prerequisite of not influencing forecast accuracy, this method largely shortens the practice time of model, enhances the speed of practice, and avoids neural-network getting involved in local optimal solution. Based on model of photovoltaic system, the daily total solar-radiation could be obtained binding with the prediction data of daily total solar-radiation.
Keywords :
neural nets; photovoltaic power systems; solar radiation; photovoltaic generation; photovoltaic grid connected generation; solar energy; solar radiation; transfer function; wavelet neural network; Arrays; Artificial neural networks; Photovoltaic systems; Prediction algorithms; Predictive models; Solar radiation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Power and Energy Engineering Conference (APPEEC), 2011 Asia-Pacific
Conference_Location :
Wuhan
ISSN :
2157-4839
Print_ISBN :
978-1-4244-6253-7
Type :
conf
DOI :
10.1109/APPEEC.2011.5749174
Filename :
5749174
Link To Document :
بازگشت