Power system transient stability evaluation method based on deep learning technology

Abstract

The invention relates to a power system transient stability evaluation method based on a deep learning technology. Firstly, a time domain simulation method is used to generate a sample set {x<0>, y<0>}; characteristic variable vectors are then extracted according to the sample set, and a training set {x<1>, y<0>} is formed, wherein the training set is the characteristic variable vector set; training parameters are determined, a stacked automatic encoder is trained based on the training set, characteristic extraction is carried out on the training set to generate a calculation set {x<2>, y<0>};and finally, based on the calculation set, classification model training is carried out on a convolution neural network, and a power system transient stability evaluation model is formed. The stackedautomatic encoder is used to carry out layer-by-layer characteristic extraction on the characteristic variable vectors, a hidden data mode is mined, high-order characteristics more facilitating transient stability evaluation are formed, the convolution neural network is further used to build a stable classification model, the evaluation performance of the model is thus ensured, the misjudgement rate of unstable samples can be reduced, noise interference in a wide area measurement system of the power system can be effectively overcome, and an important significance is provided for online safeand stable evaluation on the power system.

Description

technical field [0001] The invention belongs to the field of power system automation, and relates to a power system transient stability evaluation method based on a deep learning technology. Background technique [0002] With the rapid development of the economy, the interconnection of large-scale power grids has made the connection between power grids more and more closely. On the one hand, the interconnection of cross-regional power grids can further rationally utilize the overall resources and bring huge economic benefits; but on the other hand On the one hand, because the stability of the interconnected power grid is not equivalent to simply superimposing the stability of the sub-grid, but presents more complex dynamic characteristics, and at the same time, the safety and stability margin of the power system is reduced, and the scope of the fault spread becomes larger. Once a cascading failure occurs, it may cause power outages throughout a large area. In addition, the ...

AI Technical Summary

Problems solved by technology

[0003] The traditional time-domain simulation method is computationally intensive and time-consuming, and is not suitable for online transient stability assessment

The current online power system transient stability assessment method is mainly based on machine learning methods, but this method has the following disadvantages: (1) it is easy to overfit under the interference of power grid data noise, resulting in weak model generalization ability; (2) it is not effective Reduce the misjudgment rate of unstable samples

Images