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

Table 5

The performance of AGBO-Pro under different sizes of the embedding layer dimension.

Embedding dimension	MAE	RMSE	MAPE
Measurement time: 32	5.370 ± 0.201	6.751 ± 0.279	0.0878 ± 0.003
Date type: 16
Primary time type: 16
Secondary time type: 16
Measurement time: 64	5.131 ± 0.093	6.514 ± 0.152	0.0839 ± 0.001
Date type: 32
Primary time type: 32
Secondary time type: 32
Measurement time: 128	5.224 ± 0.120	6.596 ± 0.209	0.0854 ± 0.002
Date type: 64
Primary time type: 64
Secondary time type: 64