Dominant instability mode recognition model construction and application method based on graph neural network

Abstract

The invention discloses a dominant instability mode recognition model construction and application method based on a graph neural network and belongs to the field of power system stability judgment. The weighted graph structure constructed by the method can better reflect the topology of the power grid. Before model training, a corresponding map structure is pre-constructed according to the powergrid topology of the sample set; in the training process, the effect of the graph structure is equivalent to the effect of converting original matrix type data into graph structure data, and a test result shows that compared with a convolutional neural network method without considering topology, the graph neural network method considering the topological structure of the power grid has higher discrimination precision; according to the method, weighting processing is performed on the graph structure formed according to the power grid topology by adopting the admittance of each transmission line, so the topological information of the power grid can be further enhanced, the model is enabled to better fit the special graph structure of the power grid, the power grid topological characteristics contained in the input graph structure are enhanced, and the model is enabled to have better judgment accuracy.

Description

technical field [0001] The invention belongs to the field of power system stability judgment, and more specifically relates to a method for constructing and applying a dominant instability pattern recognition model based on a graph neural network. Background technique [0002] With the comprehensive development of all aspects of human society, national electricity consumption has become an important indicator of social economy, and the stability of power system operation is closely related to the sustainable development of social economy. The stability of the power system means that the system can still reach a new equilibrium point and continue to operate stably after being disturbed. Specifically, it can be divided into voltage stability, power angle stability and frequency stability. [0003] my country's power system is currently in the process of transforming from power system automation to intelligence. The scale of long-distance large-capacity high-voltage direct curr...

AI Technical Summary

Problems solved by technology

[0004] Traditional machine learning methods require experts to manually extract features, rely heavily on expert experience and have certain subjectivity, and it is difficult to guarantee the applicability of the model

The deep learning method that has emerged in recent years has a strong feature extraction ability, which can realize end-to-end learning from original data to the target, without relying on experts for tedious feature extraction engineering, and is now applied to stability analysis. The deep learning methods in the field usually ignore the important feature of the power grid topology, and the power grid topology has very important reference significance for judging the instability mode of the power system after a fault.

Studies have shown that slight changes in the power grid topology (such as adding or removing lines, cutting off generators, etc.) may greatly change the robustness of the system, which in turn affects the identification of instability modes after faults.

In addition, the power grid topology cannot remain unchanged during the operation process. The deep learning methods used in the field of stability analysis at this stage, such as CNN, LSTM, etc., cannot adapt well to changes in the power grid topology, and the judgment is accurate in the case of topology changes. rate will drop significantly

Images