Ultra-short-term wind power prediction method and device

Abstract

The embodiment of the invention discloses an ultra-short-term wind power prediction method and device. The method comprises the following steps: acquiring historical power data of each wind power motor and various characteristic data influencing wind power; establishing a characteristic matrix of each wind power generator according to the historical power data of each wind power generator and various characteristic data influencing the wind power; according to the characteristic matrix of each wind generator, calculating a plurality of correlation coefficients among the wind generators; constructing a comprehensive correlation coefficient matrix among the wind driven generators according to the various correlation coefficients among the wind driven generators; determining input characteristic parameters required by power prediction of each wind generator according to the comprehensive correlation coefficient matrix among the wind generators; establishing a plurality of prediction models according to input characteristic parameters required by power prediction of each wind generator; and training according to each prediction model to obtain a corresponding power prediction result, and solving by adopting a clustering algorithm to obtain an optimal power prediction result.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of wind power forecasting, and in particular to a method and device for ultra-short-term wind power forecasting. Background technique [0002] Traditional wind power forecasting methods are divided into physical models and statistical models. With the development of big data technology, artificial intelligence technology is applied to wind power forecasting. However, there are few studies on offshore wind power prediction. Due to the large specific heat capacity of seawater, the obvious influence of wind waves and wind turbine wakes, the prediction methods of land wind farms are difficult to adapt to offshore wind power prediction. In recent years, deep learning models have also been gradually applied to offshore wind power prediction, but most of them predict the wind farm as a whole without considering the influence of the wake of the wind turbines in the wind farm. Therefore, th...

AI Technical Summary

Problems solved by technology

However, there are few studies on offshore wind power prediction. Due to the large specific heat capacity of seawater, the obvious influence of wind waves and wind turbine wakes, the prediction methods of land wind farms are difficult to adapt to offshore wind power prediction.

In recent years, deep learning models have also been gradually applied to offshore wind power prediction, but most of them predict the wind farm as a whole without considering the influence of the wake of the wind turbines in the wind farm.

Images