.png){kind=icon}
.png){kind=icon}
Return
Batch Assessment of Short-Term Voltage Stability Based on Proactive Searching of Critical Operating Point
.png){kind=icon}
PRE
AI
Z
Y
X
Y
G
江
S
DOI：10.1109/TPWRS.2026.3674313.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Short-term voltage stability assessment (STVSA) plays a critical role in ensuring the stable operation of power systems, yet it suffers from excessive time consumption and computational burdens. While existing data-driven approaches accelerate the assessment by replacing time-domain simulations, this letter proposes a proactive search method of critical operating point (OP) in extensive OP space to further enhance the efficiency of batch STVSA. First, by predicting the voltage stability index through a convolutional neural network (CNN) to proactively identify critical OPs, the assessment focuses on the OPs with the lowest stability margins. Then, leveraging Shapley additive explanations (SHAP) analysis, substantial OPs with elevated instability severity are proactively searched for targeted assessments. This methodology effectively enhances the efficiency of STVSA by eliminating redundant assessments of evidently stable OPs. Case studies on a realistic 10,000-bus test system in the China Southern Power Grid validate the accuracy and efficiency of the proposed approach.
Keywords:
Batch assessment
convolutional neural network
proactive searching
SHAP
short-term voltage stability
voltage stability index
Journal
IF:
7.2
Papers:
1.1W
Citations:
5.0W
Organization
Cited Papers