Short-Term Prediction Of Wind Power

Chinese wind plants are large-scale plants and most of the them are located in where the load is few. It’s a challenge to the power system safely and stably operation that the wind’s intermittence and random which would be an obstacle to the wind power development in the future. Taking a wind power plant as an example, the paper studied some kinds of forecasting models. The paper’s main works are as follows:The study on statistical rules of wind farm parameters was done first. Some conclusions will be used later.The most commonly used linear prediction model:time series prediction model was compared with nonlinear prediction model:the neural network to make sure that the neural network can improve the prediction accuracy, and prediction error occurs with the seasons change in the law.Compared power curve predicted in the same fan for different periods and different fan for the same periods; Compared wind power predicted by the power curve with wind power pedicted by the direct prediction to draw the conclusions that direct prediction of wind farm power closest to the actual value.According to the high randomicity of wind power, the wind power combined prediction model based on maximum information entropy theory was built to improve prediction precision, which considered the high order moments. The application example showed that the model can improve the prediction precision effectively.