Table 8 Baseline forecasting performance of deep learning models before feature selection (wind forecasting).

From: Optimizing solar and wind forecasting with iHow optimization algorithm and multi-scale attention networks

Model

MSE

RMSE

MAE

MBE

\(\varvec{r}\)

\(\varvec{R^2}\)

RRMSE

NSE

WI

MSAN

0.0105

0.0055

0.0054

0.0051

0.8432

0.8558

23.49

0.8638

0.8592

LSTM

0.1226

0.0543

0.0504

0.0788

0.8033

0.8159

25.70

0.8546

0.7399

GRU

0.3290

0.0599

0.0554

0.0876

0.6960

0.7086

26.53

0.8017

0.6840

GANT

0.7110

0.1348

0.1241

0.1857

0.6597

0.6723

27.11

0.7776

0.6200

ARN

0.8443

0.1563

0.1443

0.9258

0.6412

0.6537

27.54

0.7517

0.5536

Back to article page