Wind power plant short-term power prediction method based on feature selection and multi-level deep transfer learning

Abstract

The invention discloses a wind power plant short-term power prediction method based on feature selection and multi-level deep transfer learning, and the method comprises the steps: dividing collected data into two data sets which are respectively used as a target wind power plant and a source wind power plant for transfer learning; firstly, subjecting data samples of a source wind power plant to multi-level division according to the degree of correlation with a target wind power plant, then creating a multi-level deep migration learning model of the target wind power plant based on the multi-level data samples of the source wind power plant, and finally, optimizing the multi-level deep migration learning model by adopting a feature selection method. Through prediction of the method, the data training scale can be reduced, data overfitting is avoided, and the method has popularization value.

Description

technical field [0001] The invention relates to a short-term power prediction method of a wind farm based on feature selection and multi-level deep transfer learning, which belongs to the field of new energy power prediction. Background technique [0002] With the increasing installed capacity of wind power year by year, wind power has become a powerful means of new energy power generation. Therefore, the contradiction between the problem of wind power generation and the growing demand for electricity has become increasingly prominent. The randomness and instability of wind power generation have brought difficulties to wind power grid integration, so the demand for wind power prediction continues to grow. [0003] Due to the continuous transformation and maintenance of wind farms in actual operation, and the short running time of wind power grid connection, the cumulative data of wind power operation is less, which has a great impact on the prediction accuracy of network mod...

AI Technical Summary

Problems solved by technology

[0003] Due to the continuous transformation and maintenance of wind farms in actual operation, and the short running time of wind power grid connection, the cumulative data of wind power operation is less, which has a great impact on the prediction accuracy of network models that require a large amount of data for prediction.

In addition, shallow neural networks are less effective in processing complex information, so the short-term power prediction of wind farms still needs to be greatly improved

Images