Wind power plant distributed subgradient voltage control method based on data driving sensitivity

Abstract

The invention discloses a wind power plant distributed subgradient voltage control method based on data-driven sensitivity, and the method comprises the steps: constructing a training sample set through a wind power plant integrated controller according to the historical measurement data of each node, and obtaining a dimension-raised input variable sample set through dimension-raised function transformation; based on the output variable sample set and the input variable sample set after dimension raising, calculating a data-driven linearization power flow matrix and sensitivity between node voltage and reactive power, and issuing the data-driven linearization power flow matrix and the sensitivity to each fan controller; each fan controller measures the voltage of the node and exchanges a measurement result with an adjacent node so as to calculate a local objective function gradient and a reactive power set value; and each fan controller calculates a cyclic reactive power set value and issues the cyclic reactive power set value to the fan for adjustment. Compared with the prior art, the method has the advantages that the historical measurement data is fully utilized to correct the distributed voltage control iteration direction, the influence of the inaccurate model on the distributed iteration convergence and the control effect is avoided, and the method is suitable for rapid wind power plant voltage control.

Description

technical field [0001] The invention belongs to the technical field of power system operation and control, in particular to a distributed sub-gradient voltage control method for wind farms. Background technique [0002] With the development of economy and society, the problem of environmental pollution caused by energy supply has become increasingly prominent, and the innovation, transformation and upgrading of modern energy systems have become inevitable. As one of the typical forms of new energy power generation, wind power has continuously increased its grid-connected penetration rate. However, due to the inherent uncertainty of wind power generation, wind farm power output often exhibits significant fluctuations. Because new wind turbines mostly use power electronic converters to achieve grid-connected power generation, their dynamic characteristics change rapidly and are more complex, which brings great challenges to the safe operation of wind farms. The injection of ...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the voltage control of wind farms depends on precise model parameters, the present invention proposes a distributed sub-gradient voltage control method for wind farms based on data-driven sensitivity. Use the iterative process of distributed sub-gradient voltage control to obtain the set value of reactive power of the wind turbine controller at each node, and send it to the wind turbine for execution

Images