The influence of temperature, irradiance and shielding ratio on the output characteristic curve of photovoltaic cells was studied in this paper. In order to improve the photoelectric conversion efficiency of photovoltaic cells, combining three major factors that affect photovoltaic cells, a maximum power point tracking (MPPT) scheme based on large variation genetic algorithm was proposed. In this paper, the temperature, irradiance and shielding ratio were used as input of the neural network, a prediction model was established. This photovoltaic system was simulated in Matlab. The simulation results show that the proposed approach can track the maximum power point accurately and fast, thus the photoelectric conversion efficiency of photovoltaic cells can be improved effectively.