Decision-focused learning trains an LSTM PV forecaster on battery optimization objectives and cuts average electricity costs 3.6% versus standard two-stage forecasting despite 19.9% RMSE versus 8.2%.
Optimal schedule of grid-connected residential PV generation systems with battery storages under time-of-use and step tariffs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Decision-focused learning for optimal PV-Battery scheduling
Decision-focused learning trains an LSTM PV forecaster on battery optimization objectives and cuts average electricity costs 3.6% versus standard two-stage forecasting despite 19.9% RMSE versus 8.2%.