Research Article
Forecasting Wind Power Generation Using Artificial Neural Network: “Pawan Danawi”—A Case Study from Sri Lanka
Table 1
Performance of the algorithms for different validation percentages.
| Validation percentage | ANN training algorithm | Number of epochs | R | MSE | BIAS |
| 5 | LM | 2 | 0.94 | 0.024 | 0.078 | SCG | 14 | 0.95 | 0.021 | -0.027 | BR | 603 | 0.97 | 0.000 | 0.023 |
| 10 | LM | 4 | 0.91 | 0.114 | -0.001 | SCG | 21 | 0.96 | 0.017 | -0.182 | BR | 314 | 0.94 | 0.006 | -0.166 |
| 15 | LM | 2 | 0.97 | 0.219 | 0.010 | SCG | 19 | 0.95 | 0.163 | -0.995 | BR | 992 | 0.98 | 0.008 | -0.281 |
| 20 | LM | 2 | 0.97 | 0.127 | 0.536 | SCG | 17 | 0.95 | 0.160 | 0.539 | BR | 408 | 0.99 | 0.000 | -0.276 |
| 25 | LM | 2 | 0.97 | 0.147 | 0.522 | SCG | 17 | 0.94 | 0.168 | 0.708 | BR | 413 | 1.00 | 0.000 | -0.367 |
|
|