An Extensible Gradient-Based Optimization Method for Parameter Identification in Power Distribution Network

Table 6

The performance of AGBO-Pro under different number of the hidden layers.

Embedding dimension	MAE	RMSE	MAPE
1 hidden layer	5.131 ± 0.093	6.514 ± 0.152	0.084 ± 0.002
2 hidden layers	5.574 ± 0.285	7.048 ± 0.344	0.091 ± 0.005
3 hidden layers	5.545 ± 0.279	7.052 ± 0.397	0.091 ± 0.005

The bold values indicate that with one hidden layer, the model gains the best performance.