Short-term prediction model of module temperature for photovoltaic power forcasting based on support vector machine

To improve the prediction accuracy of photovoltaic (PV) power generation, the temperature of PV modules and its prediction is very important. A short-term step-wise temperature prediction model for PV module based on Support Vector Machine ( SVM) is proposed in this paper. Firstly, the primary impact factors of PV module temperature are determined in terms of the PV module physical characteristics and the correlation coefficient between each factor and module temperature. Secondly, two kinds of prediction models, direct and step-wise models, are built to predict module temperature respectively. For direct model, the prediction model is based on SVM using the historical data. For step-wise one, the prediction models of the primary impact factors are built at the first step and then the mapping models between module temperature and the impact factors are established. In the end, the deviations of two different kinds of prediction models are analy%ed and discussed based on actual operation data. The results indicate that the stepwise prediction model has better accuracy than the direct prediction model if other things are equal.