Power flow checking method based on graph convolution network acceleration

Abstract

The invention discloses a power flow checking method based on graph convolution network acceleration, and the method comprises the steps: firstly collecting topological data and network parameters ofa power system, generating a large number of operation states of the power system, judging whether the generated operation states of the power system are out of limit or not through a conventional power flow calculation method, and taking whether the operation states of the power system are out of limit or not as a label; obtaining a power flow check data set of the power system; dividing the dataset into a training data set and a test data set; then establishing a graph convolution network model, and training to obtain the graph convolution network model used for accelerating power flow check; and finally, predicting the actual power system operation state data to obtain a power flow out-of-limit judgment result. According to the method, the graph convolution network model is establishedand trained to obtain the classification model capable of judging power flow out-of-limit, so that the calculation speed and efficiency of large-scale power grid power flow check can be improved.

Description

technical field [0001] The invention belongs to the field of static safety checking of power grids, and in particular relates to a power flow checking method based on graph convolution network acceleration. Background technique [0002] As the scale of the large power grid system becomes larger and the component models become more refined, the computational complexity of modern power system analysis becomes higher and the amount of calculation becomes larger; in addition, renewable energy, distributed storage and other new technologies are also becoming more and more complex. These trends have greatly increased the computing power requirements for power system analysis and calculation. Traditional power flow calculations use numerical calculation methods to iteratively perform calculation tasks, which cannot meet the real-time requirements of system calculations. In addition, in power grid power flow calculation, the Newton-Raphson method needs to solve a correction equatio...

AI Technical Summary

Problems solved by technology

Traditional power flow calculations use numerical calculation methods to iteratively perform calculation tasks, which cannot meet the real-time requirements of system calculations.

In addition, in the grid power flow calculation, each iteration of the Newton-Raphson method needs to solve a correction equation. When the node scale becomes larger, the calculation amount will increase sharply

Images