Table 3 Advance models comparison of results.

From: Optimizing load demand forecasting in educational buildings using quantum-inspired particle swarm optimization (QPSO) with recurrent neural networks (RNNs):a seasonal approach

Metric

Ensemble Methods

Hybrid Models

LSTM

GRU

Transformer

MAE

14.8

13.5

12.8

13.1

11.5

MSE

480.25

430.55

400.12

410.78

360.5

RMSE

21.9

20.75

20

20.3

18.98

R²

0.94 (94%)

0.95 (95%)

0.96 (96%)

0.95 (95%)

0.97 (97%)

MAPE

8.75%

7.95%

7.10%

7.30%

6.50%

sMAPE

7.20%

6.85%

6.20%

6.50%

5.80%

MASE

0.43

0.38

0.36

0.37

0.32

Back to article page