Title :
Short-Term PV Generation System Direct Power Prediction Model on Wavelet Neural Network and Weather Type Clustering
Author :
Ying Yang ; Lei Dong
Author_Institution :
Sch. of Autom., Beijing Inst. of Technol., Beijing, China
Abstract :
With the increase of the capacity of PV generated systems, how to eliminate the problem caused by the randomness of power output for photovoltaic system becomes more significant. Most of the existing photovoltaic prediction is Based on the solar radiation. However, it´s difficult to implement in China due to insufficient solar radiation station available and poor forecasting performance. In addition, indirect forecasting cannot consider the factors related with PV system. A novel power forecasting model using historical power is proposed to solve the problems. Furthermore, in order to adapt sudden weather changes, the future weather type was recognized by using self-organizing feature map(SOM). Then, PV power generation in each weather type could be forecasted from its corresponding forecast network and the over fitting issue of single network model could be addressed. Wavelet neural network is combined with wavelet analysis and neural network. It is compatible with the good time-frequency property and good fault tolerant ability of neural network. Wavelet neural network can optimize the forecasting model. The experimental results indicate that the prediction has high precision and can be applied in stable operation of photovoltaic generation system.
Keywords :
photovoltaic power systems; self-organising feature maps; solar power stations; solar radiation; wavelet transforms; fault tolerant ability; historical power; power forecasting model; self organizing feature map; short term PV generation system direct power prediction model; solar radiation; time frequency property; wavelet analysis; wavelet neural network; weather type clustering; Meteorology; Neural networks; Neurons; Photovoltaic systems; Predictive models; Solar radiation; Training; Direct prediction; PV generation system; Wavelet neural network; Weather type clustering;
Conference_Titel :
Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2013 5th International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-0-7695-5011-4
DOI :
10.1109/IHMSC.2013.56