Data completing of missing wind power data based on adaptive BP neural network

The integrity of wind power output data is of great significance for the accurate prediction of wind power and the utilization of wind energy. In this paper, it is found that the power output affected by many factors, through the analysis of the mathematical model of wind turbine, and the solution of the specific expressions of the relationship with the traditional mathematical methods is hard to find. Based on the measured data of wind field, such as fan current, rotor speed, wind direction, and so on, a kind of model based on adaptive BP neural network is proposed to fill the missing wind power data. The simulation experiment shows that the accuracy rate and the average relative error of complete data get better results, besides the quality of completed data is improved effectively.