Prediction Of Wind Power Based On Ipso-svm Mode Decomposition

With the non-stationary nature and volatility of wind energy,grid-connected wind power on a great scale will affect the balance operation of power system and power distribution,even threatening the security and development of the power grid.Searching for a excellent prediction of wind power is not only conducive to the power grid scheduling,but also can improve the efficiency of wind power utilization,what is more,ensure the stable working of the power grid.It is a great importance to do the research of the prediction technique of the wind power for a better development of the wind electricity.A series of studies are found based on measured wind speed and wind power data in wind farm: both wind speed and wind power are very random data;they have strong characteristics of nonlinear and non-stationary,At first,Using the Support Vector Machine(SVM)as the basic tool of modeling and building wind power prediction model.Then introduced Improved Particle Swarm Optimization(IPSO)to optimize the parameters choice of the SVM.The combination of the two predictive models increase the accuracy of wind power forecasting by means of the simulation results.according to the non-stationary and nonlinear characteristics of the wind speed and wind power data,the empirical mode decomposition(EMD)algorithm is used to decompose the data into a series of relatively stable components,then the Improved Particle Swarm Optimization-Support Vector Machine(IPSO-SVM)prediction model of each decomposed component is established.The inputs of the forecasting model are historical wind power data and historical wind speed data.Forecast result of wind power is made with wind power curve.Through the means of the simulation results and error comparison,It shows that the direct prediction model based on EMD-IPSO-SVM has the smallest forecast error,and effectively improves the prediction of wind power.