The power prediction for photovoltaic (PV) power plants has significant importance for their grid connection. Due to PV power’s periodicity and non-stationary characteristics, traditional power prediction methods based on linear or time series models are no longer applicable. This paper presents a method combining the advantages of the wavelet decomposition (WD) and artificial neural network (ANN) to solve this problem. With the ability of ANN to address nonlinear relationships, theoretical solar irradiance and meteorological variables are chosen as the input of the hybrid model based on WD and ANN. The output power of the PV plant is decomposed using WD to separated useful information from disturbances. The ANNs are used to build the models of the decomposed PV output power. Finally, the outputs of the ANN models are reconstructed into the forecasted PV plant power. The presented method is compared with the traditional forecasting method based on ANN. The results shows that the method described in this paper needs less calculation time and has better forecasting precision.

PV nonlinear characteristics caused by complex external environment and the complexity of PV maximum power point locations distribution influence the design and optimization of photovoltaic maximum power tracking algorithm. Based on PV equivalent circuit model, unknown parameters of PV model are solved by an iterative algorithm. And then, a mathematical model of the PV array full of working conditions are built. Typical shading and external environmental conditions are designed, then distance analysis method are used to study the distribution of PV maximum power point. Simulation results show that the voltage of PV maximum power point mainly affected by temperature and uneven lighting conditions will affect the number of maximum power point of PV.