Active learning, used to train random-forest surrogates inside multilevel Monte Carlo, reduces the number of exact simulations needed for resource adequacy estimates within a fixed time budget.
Minimizing unserved energy using heterogeneous storage units,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MLMC-based Resource Adequacy Assessment with Active Learning Trained Surrogate Models
Active learning, used to train random-forest surrogates inside multilevel Monte Carlo, reduces the number of exact simulations needed for resource adequacy estimates within a fixed time budget.