EMGRL, an actor-critic ensemble of ARIMA, LightGBM, LSTM, and SGNN with a GNN-based spatial state embedding, is claimed to beat baselines on NREL and GEFC wind datasets.
The first part involves using real-time wavelet packet decomposition enhanced deep echo state network to construct the basic model with different vanishing moments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Applying Ensemble Models based on Graph Neural Network and Reinforcement Learning for Wind Power Forecasting
EMGRL, an actor-critic ensemble of ARIMA, LightGBM, LSTM, and SGNN with a GNN-based spatial state embedding, is claimed to beat baselines on NREL and GEFC wind datasets.