Table 5 Forecasting performances of the networks trained with all features.
From: Parallel boosting neural network with mutual information for day-ahead solar irradiance forecasting
Location | Model | RMSE | MAE | MSE | MAPE | NRMSE |
|---|---|---|---|---|---|---|
Islamabad | CatBoost | 30.2 | 22.19 | 912.3 | 0.72 | 0.63 |
XgBoost | 52.69 | 37.42 | 2776.4 | 1.13 | 0.49 | |
RF | 26.53 | 18.5 | 703.86 | 0.56 | 0.55 | |
LSTM | 93.44 | 16.99 | 8731.81 | 3.95 | 1.94 | |
GRU | 80.99 | 53.74 | 6560.94 | 1.96 | 1.68 | |
PBNN | 25.18 | 17.39 | 633.96 | 0.49 | 0.52 | |
San Diego | CatBoost | 43.98 | 31.68 | 1934.79 | 0.69 | 0.84 |
XgBoost | 49.31 | 34.48 | 2432.18 | 0.69 | 0.94 | |
RF | 31.71 | 53.86 | 2900.91 | 0.64 | 1.03 | |
LSTM | 21977.2 | 148.25 | 115.41 | 2.39 | 2.88 | |
GRU | 113.81 | 65.18 | 1.34 | 1.08 | 2.18 | |
PBNN | 36.74 | 21.86 | 1349.92 | 0.46 | 0.7 |
