Keywords
TSA;GSTGNN;GRU;KNN;data visualizatio
Abstract
With the continuous expansion of UHV AC/DC interconnection scale, on‑line high‑precision and fast transient stability assessment (TSA) is very important for the safe operation of power grid. To this end, a TSA method based on gating spatial temporal graph neural network (GSTGNN) is proposed and the time adaptive method is used to improve the accuracy and speed of TSA at the same time. Firstly, in order to reduce the impact of dynamic topology on TSA after fault removal, GSTGNN is used to extract and fuse the key features of topology and attribute information of adjacent nodes to learn the spatial data correlation and improve the evaluation accuracy. Then, the extracted features are input into the gated recurrent unit (GRU) to learn the correlation of data at each time, and adjust the stability threshold to quickly output accurate evaluation results. Meanwhile, in order to avoid the influence of the quality of training samples, the improved weighted cross entropy loss function with K nearest neighbor (KNN) idea is used to deal with the unbalanced training samples. Through the analysis of an calculation example, it is verified from the data visualization that TSA method can effectively improve assessment accuracy and shorten assessment time.
DOI
10.19781/j.issn.1673-9140.2023.02.024
First Page
214
Last Page
223
Recommended Citation
LIU, Jianfeng; YAO, Chenxi; and CHEN, Lele
(2023)
"Power system transient stability assessment based on gating spatial temporal graph neural network,"
Journal of Electric Power Science and Technology: Vol. 38:
Iss.
2, Article 24.
DOI: 10.19781/j.issn.1673-9140.2023.02.024
Available at:
https://jepst.researchcommons.org/journal/vol38/iss2/24