Table 4 Performance comparison of models using 3 inputs from previous years.
From: Electric-load forecasting using interval models based on granularity and justifiable principles
Model | Train RMSE | Train MAE | Train \(R^2\) | Train MAPE | Test RMSE | Test MAE | Test \(R^2\) | Test MAPE |
|---|---|---|---|---|---|---|---|---|
Linear regression | 367.62 | 276.65 | 0.9074 | 6.37 | 352.02 | 265.37 | 0.9152 | 6.09 |
Decision tree | 0.00 | 0.00 | 1.0000 | 0.00 | 444.67 | 320.61 | 0.8647 | 7.28 |
SVM | 438.29 | 332.62 | 0.8684 | 7.98 | 435.37 | 330.38 | 0.8703 | 7.88 |
KNN | 285.03 | 209.61 | 0.9443 | 4.77 | 337.80 | 249.89 | 0.9219 | 5.70 |
Bagging | 148.23 | 101.89 | 0.9849 | 2.33 | 347.15 | 257.60 | 0.9175 | 5.88 |
Neural net | 369.43 | 276.46 | 0.9065 | 6.34 | 356.41 | 265.68 | 0.9131 | 6.08 |
