Kriging-based active learning efficiently maps rare instability regions in uncertain power systems and estimates their small probabilities, outperforming random forest active learning and non-active methods on IEEE 59-bus and WECC 240-bus test cases.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Probabilistic Assessment of Rare Transient Instability Events via Kriging-based Active Learning Framework
Kriging-based active learning efficiently maps rare instability regions in uncertain power systems and estimates their small probabilities, outperforming random forest active learning and non-active methods on IEEE 59-bus and WECC 240-bus test cases.