Table 4 Evaluation metrics on validation set ordered by increasing R² (Lower to higher Efficiency).
From: Comparative analysis of deep learning architectures in solar power prediction
Model | RMSE | MAE | MAPE | R² |
|---|---|---|---|---|
Transformer | 864.4696 | 755.1639 | 101714.3527 | 0.1712 |
LSTM | 539.8949 | 427.3706 | 33203.2621 | 0.6767 |
GRU | 513.7007 | 394.8666 | 33446.1366 | 0.7073 |
CNN | 495.7869 | 370.4419 | 16653.6720 | 0.7274 |
InformerLite | 480.1903 | 351.7369 | 39847.8133 | 0.7443 |
SimpleRNN | 472.0302 | 355.3144 | 21852.0857 | 0.7529 |
TCN | 439.9661 | 300.8601 | 15749.0408 | 0.7853 |
Autoencoder | 427.0279 | 285.8551 | 6525.7144 | 0.7978 |
