Power system transient stability control method and system based on graph neural network

Abstract

The invention discloses a power system transient stability control method and system based on a graph neural network. The method comprises the following steps: acquiring a power system feature vector and an adjacent matrix; inputting the adjacency matrix and the power system feature vector into a pre-trained graph neural network evaluation model, and outputting a transient stability margin evaluation value of the power system; judging the transient power angle stability of the power system based on the transient stability margin evaluation value; if not, updatiing the control strategy, and if yes, achieving transient stability control of the power system based on the corresponding control strategy when the transient power angle stability of the power system is judged to be stable. According to the method, the topological information of the power grid is considered by using the graph neural network, the transient stability margin of the system can be evaluated in real time, and the emergency control strategy can be iteratively generated and executed, so that synchronous operation of the synchronous generator group in the system after a large disturbance fault can be ensured.

Description

technical field [0001] The invention belongs to the technical field of safety and stability control of large power grids, relates to the field of power system transient stability control, and in particular relates to a graph neural network-based power system transient stability control method and system. Background technique [0002] In recent years, with the continuous expansion of the scale of the power system and a large number of intermittent new energy sources, the characteristics of the power grid have become increasingly complex, and the difficulty of ensuring the safe and stable operation of the system has gradually increased; Among them, for the unstable system after a fault, effective Emergency control measures are an important means to prevent further development of faults and avoid large-scale blackouts. [0003] At present, the emergency control of power system is still in the stage of "offline decision-making, real-time matching". Offline decision-making is ge...

AI Technical Summary

Problems solved by technology

It is difficult for conventional machine learning models to consider power grid topology information. The rapidly emerging graph neural network method in recent years provides a new solution for the utilization of power grid topology information.

Images