Machine learning estimates of marginal costs guide an iterative TSA algorithm to produce an aggregated GEP model that preserves active constraints and yields exact solutions.
Towards exact temporal aggregation of time-coupled energy storage models via active constraint set identification and machine learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Machine Learning for Exact Time Series Aggregation in Generation Expansion Planning with Energy Storage
Machine learning estimates of marginal costs guide an iterative TSA algorithm to produce an aggregated GEP model that preserves active constraints and yields exact solutions.