Research Article
An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network
Table 4
The performance of AGBO-Pro under different learning rates.
| Learning rate | MAE | RMSE | MAPE |
| 5e − 2 | 5.850 ± 0.192 | 7.365 ± 0.266 | 0.0956 ± 0.00315 | 1e − 2 | 5.486 ± 0.242 | 6.916 ± 0.266 | 0.0897 ± 0.0028 | 5e − 3 | 5.131 ± 0.093 | 6.514 ± 0.152 | 0.0839 ± 0.0015 | 1e − 3 | 5.486 ± 0.172 | 6.916 ± 0.242 | 0.0897 ± 0.0028 | 1e − 4 | 8.231 ± 0.327 | 11.121 ± 0.493 | 0.135 ± 0.0053 | 1e − 5 | 8.545 ± 0.057 | 11.454 ± 0.326 | 0.140 ± 0.0009 |
|
|
The bold values indicate that with the learning rate 5e − 3, the model has the lowest values in three evaluation functions.
|