Wind turbine generator output power modeling method and system based on Gaussian process regression

Abstract

The invention discloses a wind turbine generator output power modeling method based on Gaussian process regression. The method comprises the following steps: firstly, determining a Gaussian process structure; then, constructing a kernel function based on a characteristic relationship between an input variable and an output variable; and finally, based on the Gaussian process structure and the constructed kernel function, establishing a wind turbine generator output power model. In addition, the invention further provides a wind turbine generator output power modeling system based on Gaussian process regression. According to the wind turbine generator output power modeling method and system based on Gaussian process regression, the model structure of the Gaussian process is improved, the understandability of a wind turbine generator output power model is improved, and according to the characteristic relationship between the input variable and the output variable, and when the input variable is input, a kernel function conforming to the characteristic relationship of the input and output variables is constructed as a new covariance function, so that the contribution of the input variable to the output variable is clearer.

Description

technical field [0001] The invention relates to the field of electric power, in particular to a Gaussian process regression-based modeling method and system for the output power of wind turbines. Background technique [0002] The power generation performance of wind turbines marks the economic benefits of wind power enterprises, and the output power of wind turbines can reflect the power generation performance of the wind turbines. However, wind power companies need to judge whether the power generation performance of wind turbines is abnormal through the output power of wind turbines. This problem belongs to the supervised learning problem in machine learning. Machine learning is usually used to model and learn the mapping between input and output according to the training set. Relationship, so that the corresponding predicted value is obtained given a new input, which belongs to the regression problem. Furthermore, to learn the mapping relationship between input and outpu...

AI Technical Summary

Problems solved by technology

[0007] Based on this, it is necessary to provide a modeling method and system for wind turbine output power based on Gaussian process regression for the modeling of wind turbine output power

Images