The Research Of Power Combination Forecasting Model In Wind Turbine

In recent years,the development of wind power has entered a period of rapid development.With the increasing of wind power capacity and penetration,the adverse impacts to the grid have become more and more prominent.The contradiction between the demand of wind farm connected into the grid and the receptivity of the grid is getting expanded.Because wind power has a strong randomness,it makes difficult to formulate rational power plan,which leads to the dispatching department making a reasonable scheduling for wind power.Firstly,this paper introduces the development of wind power and the potential of wind power development,introduces the importance of wind power and the existing wind power calculation method.The applicability of the Markov chain to wind power prediction is discussed.Then,a prediction method based on Markov chain model is introduced,This paper discusses the prediction steps of the Markov chain model based on the absolute distribution,selects the wind power of the actual production environment as the data source,and simulates the calculation and calculation.The influence of the state space on the prediction accuracy is expounded and the best state space number is choosed.The results show that However,the single prediction method has a certain degree of validity and accuracy,but there are always different degrees of limitations,in order to further improve the accuracy of prediction,and finally learn from the information theory of information entropy The combination of the continuous prediction method and the Markov chain prediction theory is combined,and the weighting coefficient in the combined model is determined by the entropy method,and the combined forecasting model is established.The simulation results show that the combined forecasting method can make up for the shortcomings of each method,so that the advantages of the two methods are complementary,the prediction error is reduced,the prediction accuracy is improved and effectively improve the accuracy of wind power prediction.