Research Article

Application of Multiattention Mechanism in Power System Branch Parameter Identification

Table 1

Experimental results of grid dataset on index line susceptance .

Line susceptance None50 dB30 dBdropDatadropEdge50 dB + DD + DE

LinearRegression0.00060.13390.44020.12730.18620.2569
SVR0.13290.21611.49230.11810.17800.2399
RF0.07850.15580.22980.17950.18980.2335
XGBoost0.08560.17320.24310.21240.23730.2542
lightGBM0.13240.19880.35620.31220.32420.3541
KNN0.09430.15240.23450.24620.21450.2451
Bagging0.05410.14510.23310.21430.23640.2442

FCN0.63140.76030.84300.81290.87240.8133
GTN0.14130.16580.19920.16960.16520.2188

Here we choose RMSE as the comparative index. The highest values for the different metrics are highlighted in bold.