LAUSR

With the increasing contribution of the power production by the photovoltaic (PV) systems to the electricity supply, the PV power forecasting becomes increasingly important. There are many factors influencing the forecasting performance, such as the air temperature, humidity, insolation, wind speed, wind direction and so on. This study proposes a Takagi-Sugeno (T-S) fuzzy model-based PV power short-term forecasting approach. First, by means of the correlation analysis, the influential factors are selected as the model inputs. Then, the fuzzy c-mean clustering algorithm and the recursive least squares method are used to identify the antecedent and the consequent parameters. The performance of the proposed forecasting approach is tested by using a large database of measurement data from the 433 kW PV array at St Lucia campus of The Queensland University of Australia. The forecasting results are compared with the support vector machine (SVM), the hybrid of empirical mode decomposition and SVM, the back propagation neural network and the recurrent neural network. The results indicate that, compared with the existing approaches, the proposed T-S fuzzy model-based forecasting approach is simpler and can forecast more accurately.