A system and method for determining transient stability of power systems based on deep learning

Abstract

The invention discloses a power system transient stability judgment system and method based on deep learning, which belongs to the technical field of power system dynamic security assessment. The system of the invention includes four modules: sample acquisition, feature extraction, sample expansion, and stability judgment. At the same time, the method of system implementation is disclosed. Using the deep self-encoder to extract the characteristic data of the power system sample data reduces the dimension of the sample, which can effectively save computing power and computing time; using the confrontation generation network to generate pseudo-sample data, expand the scale of the sample set, The stability judgment module can better judge the transient stability of the power system and improve the accuracy of stability judgment; the use of deep convolutional neural network to build the power system transient stability judgment module can make more real-time and accurate judgments Transient stability of power systems.

Description

technical field [0001] The present invention relates to the technical field of power system dynamic security assessment, in particular to a system and method for judging the transient stability of a power system based on deep learning. Background technique [0002] At present, the scale of my country's power system continues to expand, and maintaining the safe and stable operation of the power system has become a top priority, and the transient stability of the power system plays a vital role in safe and stable operation. Transient stability control is the first line of defense for the stable operation of the power system, and has particularly important research value, so how to accurately and quickly judge the transient stability of the power system is very important for the actual operation of the power grid. [0003] Among the existing power system transient stability evaluation methods, the time-domain simulation method with the advantages of calculation accuracy is insu...

AI Technical Summary

Problems solved by technology

[0003] Among the existing power system transient stability evaluation methods, the time-domain simulation method with the advantages of calculation accuracy is insufficient in speed, and the direct method based on energy function, which has better calculation speed and accuracy, cannot be applied to complex systems.

In recent years, machine learning methods have been applied to transient stability problems, such as artificial neural networks, support vector machines and other methods, and have made great progress. However, due to their weak feature learning ability, they have high probability of misclassification and reliability. Difficult to guarantee

Deep learning methods have also been introduced into this field, such as deep belief networks and stacked autoencoders, etc., but there are still deficiencies in the processing of samples and the precise application of deep learning networks.

Images