Table 13 The comparison between the proposed method and the existing methods.

From: Learning model combined with data clustering and dimensionality reduction for short-term electricity load forecasting

Model

Summer

Winter

MAPE

RMSE

NMAE

NRMSE

MAPE

RMSE

NMAE

NRMSE

ANN

3.55 ± 1.88

219.75 ± 87.64

0.04 ± 0.02

0.05 ± 0.02

4.24 ± 0.15

454.39 ± 15.52

0.05 ± 0.0

0.08 ± 0

CNN

2.66 ± 0.1

177.37 ± 6.25

0.03 ± 0.0

0.04 ± 0.0

4.02 ± 0.13

405.79 ± 8.42

0.04 ± 0.0

0.07 ± 0.0

CNN + Proposed

2.48 ± 0.07

178.26 ± 2.55

0.03 ± 0.0

0.04 ± 0.0

3.94 ± 0.18

391.66 ± 8.79

0.04 ± 0.0

0.07 ± 0.0

LSTM

2.03 ± 0.06

138.59 ± 3.75

0.02 ± 0.0

0.03 ± 0.0

3.28 ± 0.14

339.77 ± 30.86

0.03 ± 0.0

0.06 ± 0.01

LSTM + Proposed

2.01 ± 0.07

141.16 ± 4.17

0.02 ± 0.0

0.03 ± 0.0

3.19 ± 0.08

319.26 ± 12.89

0.03 ± 0.0

0.06 ± 0.0

DLinear

4.46 ± 0.07

223.40 ± 2.17

0.04 ± 0.0

0.05 ± 0.0

8.21 ± 0.09

634.98 ± 3.16

0.08 ± 0.0

0.11 ± 0.0

DLinear + Proposed

2.86 ± 0.05

156.28 ± 1.33

0.03 ± 0.0

0.03 ± 0.0

5.79 ± 0.05

509.04 ± 2.55

0.06 ± 0.0

0.09 ± 0.0

Autoformer

4.09 ± 0.31

240.21 ± 20.89

0.04 ± 0.003

0.05 ± 0.005

12.43 ± 0.50

924.30 ± 37.72

0.13 ± 0.006

0.16 ± 0.006

Autoformer + Proposed

3.66 ± 0.27

237.11 ± 19.62

0.04 ± 0.003

0.05 ± 0.004

12.47 ± 0.89

939.39 ± 48.30

0.13 ± 0.008

0.16 ± 0.008

LSTNet

3.42 ± 0.35

225.81 ± 24.90

0.04 ± 0.004

0.05 ± 0.005

5.05 ± 0.44

453.17 ± 49.42

0.05 ± 0.004

0.08 ± 0.008

LSTNet + Proposed

3.00 ± 0.16

214.94 ± 9.29

0.03 ± 0.002

0.05 ± 0.002

4.32 ± 0.27

420.87 ± 31.69

0.05 ± 0.003

0.07 ± 0.005