Table 6 PBNN forecasting performance at different thresholds.
From: Parallel boosting neural network with mutual information for day-ahead solar irradiance forecasting
Location | Threshold level | RMSE | MAE | MSE | MAPE | NRMSE | Computational time |
|---|---|---|---|---|---|---|---|
Islamabad | Â | (\(W/m^2\)) | (\(W/m^2\)) | \((W/m^2)^2\) | (%) | (%) | (s) |
0.1 | 19.2 | 12.49 | 368.76 | 0.36 | 0.39 | 10.02 | |
0.2 | 14.06 | 8.36 | 197.77 | 0.26 | 0.29 | 9.986 | |
0.4 | 19.67 | 11.14 | 386.93 | 0.45 | 0.41 | 9.84 |
