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

Table 2

The results of parameter identification with the loss function of mean square error.

Method	MAE	RMSE	MAPE
AGBO-Pro	25.415 ± 0.855	32.511 ± 1.050	0.415 ± 0.014
AGBO	64.100 ± 0.474	65.791 ± 0.478	1.047 ± 0.008
RS	65.570 ± 0.746	67.148 ± 0.699	1.071 ± 0.012
TPE	64.689 ± 0.648	66.355 ± 0.633	1.057 ± 0.011
SA	65.894 ± 0.983	67.439 ± 0.913	1.077 ± 0.016
AO	64.5001 ± 0.7016	66.1795 ± 0.6854	1.0539 ± 0.0115
NRO	64.5174 ± 0.6998	66.1954 ± 0.6837	1.054 ± 0.0114
PSS	64.6944 ± 0.6984	66.3599 ± 0.6847	1.0571 ± 0.0114

AGBO-Pro uses mean square loss to ensure fairness in comparison. The bold values indicate that the AGBO-Pro method gains the lowest values in all three evaluation functions, viz. MAE, RMSE and MAPE, indicting its best performance.