Skip to main content

Table 7 24-h forecast metrics

From: Evaluation of neural networks for residential load forecasting and the impact of systematic feature identification

Model

MAE (kWh)

MAPE (%)

RMSE (kWh)

Adjusted R2

With CSTEP variables

 FFN

5.1261

6.15

6.5972

0.9282

 RNN

5.5766

6.7

7.1415

0.9146

 LSTM

5.4739

6.55

7.0274

0.9157

 GRU

5.3879

6.49

6.8899

0.9203

Without CSTEP variables

 FFN

5.2146

6.22

6.725

0.9252

 RNN

5.7518

6.92

7.3522

0.9082

 LSTM

5.5011

6.6

7.0516

0.9158

 GRU

5.4639

6.53

7.0212

0.9172