Research On Wind Speed-wind Power Prediction Based On Gray System Theory

Due to the non-stationary and fluctuating wind energy,large scale grid connected wind power will bring a great impact on the power grid.Accurate prediction of wind speed and wind power is not only conducive to the dispatch of power grid,but also can improve the efficiency of wind power utilization and ensure the stable operation of power grid.In this paper,the grey GM(1,1)model and the application of BP neural network are used to forecast the wind speed and wind power of the wind farm.Firstly,the grey GM(1,1)model is optimized by the numerical approximation algorithm,which aims to solve the problem of the traditional grey GM(1,1)model to predict the error of nonlinear data.The wind speed data from the actual wind farm,through mathematical derivation and improved model,gray optimized GM(1,1)model for prediction of wind speed,wind speed prediction error is significantly reduced,the relative prediction error is reduced by 32%.Based on the predicted wind speed,the temperature and wind direction in the wind field were simulated separately,and the error analysis of the results was carried out,which verified the feasibility and stability of the prediction method.Secondly,the BP neural network prediction of nonlinear have very good effect,In order to combine GM(1,1)model and BP neural network model of the proposed prediction model using grey neural network correction BP.Grey GM(1,1)model,BP neural network model and BP neural network model were used to forecast the wind power of wind farm.Thirdly,we analyze the error of the prediction results show that the improved model prediction accuracy and stability than the single model has been greatly improved,proves the validity of the model in practical application,can provide reference for power dispatch department.Finally,as a research direction for future work,this paper studies the wind speed distribution characteristics of wind farm,through the study of the annual change of wind speed and diurnal variation,the wind speed distribution has obvious seasonal characteristics.