Wind turbine power prediction method based on wake flow deflection effect and 2DJensen model

Abstract

The invention discloses a wind turbine power prediction method based on a wake flow deflection effect and a 2DJensen model. The method comprises the following steps: collecting and preprocessing SCADA data of a wind turbine in a wind field; constructing relative position coordinates of each wind turbine based on the geographic position data of the wind turbines in the wind field; determining a node set and a global attribute of the wind turbine in the wind field; determining an edge set and an adjacent matrix between the wind turbines in the wind field; constructing an input vector graph set; constructing an improved graph neural network model based on a wake flow deflection effect and a 2DJensen model; and parameter optimization is carried out according to the preprocessed SCADA data set and the input vector diagram, a wind turbine power prediction model in the wind field is determined, and prediction power of all wind turbine nodes in the wind field is determined. According to the method, the power output value of the wind turbine generator with the yaw error angle in the whole wind field under different wind conditions can be accurately predicted.

Description

technical field [0001] The invention belongs to the field of wind turbine power forecasting, and in particular relates to a wind turbine power forecasting method based on wake deflection effect and 2D Jensen model. Background technique [0002] my country is vigorously developing the new energy industry, and wind energy has become one of the more promising new energy sources because of its wide distribution and no pollution. With the continuous development of wind power technology, more and more large wind farms have emerged. Due to factors such as cost and site, large-scale wind farms will have interactions between wind turbines and complex and changeable internal wind farms. The predicted power can not only analyze the power loss of the wind farm, but also effectively improve the power generation efficiency of the wind farm by combining the predicted power with the field control system. Therefore, it is of great significance to accurately predict the power of all wind tu...

AI Technical Summary

Problems solved by technology

Due to factors such as cost and site, large-scale wind farms will have interactions between wind turbines, complex and changeable internal wind farms, etc.

Images