Short-term Prediction Of Wind Power Based On Wind Speed Correction

In the 21 century sustainable development and green development are becoming the trend of the times.That’s because the severe situation of energy crisis and ecological crisis are becoming more and more obviously.As a kind of clean renewable energy,wind energy has been favored by all countries in the world because of its large reserves and convenient development.It has become a hot spot of research and development.However,due to the volatility and intermittent ness of the wind,the wind turbine output is unstable,and the large-scale wind power grid connection has adversely affected the stable operation of the power grid.Therefore,wind power forecasting helps the power system to make reasonable scheduling decisions and ensure the safe and stable operation of the power grid.It also helps the wind farm to arrange equipment maintenance and ensure the economic benefits of wind power generation.In this paper,the empirical mode decomposition-differential autoregressive moving average model(EMD-ARIMA)is used to correct the wind speed error,and then the short-term prediction of wind power is carried out.Firstly,the EMD algorithm is applied to decompose the prediction error sequence of historical wind speed and historical NWP wind speed of wind farm,and extract the eigenmode function which contains different frequency information of the original sequence;secondly,the ARIMA time series model is established for short-term prediction of each component sequence,and the predicted results are superimposed and combined with the NWP data in the future period to obtain the revised wind speed value.Finally,according to the wind power generation.The power characteristic curve of the motor predicts the wind power after wind speed correction.After the sample data collected by the wind farm and the NWP data sequence were preprocessed,a case study was performed.The three prediction models,such as average absolute error,root mean square error and average absolute percentage error,are used to evaluate the established prediction model.The results show that the prediction accuracy is better,and the effectiveness of the wind power indirect prediction model based on EMD-ARIMA wind speed correction is verified.The prediction results of the above model are compared with the traditional ARMA model power prediction results and the uncorrected wind speed power prediction results.The results show that the wind power prediction accuracy based on EMD-ARIMA wind speed correction is higher.At the end of the paper,the work in this paper is summarized,and the content that needs further improvement is put forward.The research trend of wind power prediction is prospected.