Short-Term Wind Power Prediction Based on Phase Space Reconstruction Theory

The accession of large scale wind power will impact the planning and construction, analytical control, operation of the economy, as well as power quality of the power grid. More accurate wind power prediction can help reduce the quantity of spinning reserve and provide the grid dispatching operation a reliable foundation. Wind power has chaotic characteristic. This paper proposed a method of chaotic time series prediction based on chaotic phase space reconstruction. The forecast precision depends largely on the choice of the model parameters. In order to improve the forecast precision and generalization ability of the prediction model, this article computed with the method of C-C to optimize the phase space reconstruction parameters comprehensive. Forecasting model used weighting first-order local field method. To test the approach, the data from a wind farm of Inner Mongolia were used. Practical examples showed that the integrated approach has a very good forecast precision and good practicability.