Table 6 Comparison of comprehensive performance of different models based on regression and classification indicators.
From: Design of security situation awareness power grid SCADA system based on improved GWO-LSTM
Model | MSRE | RMSRE | RMSPR | MARE | MAE | MAPE | Accuracy (%) | F1 score (%) |
|---|---|---|---|---|---|---|---|---|
BPNN | 0.19 ± 0.02 | 0.28 ± 0.02 | 0.31 ± 0.03 | 0.24 ± 0.02 | 0.048 ± 0.002 | 0.173 ± 0.004 | 87.53 ± 0.41 | 0.84 ± 0.21 |
SVM | 0.16 ± 0.01 | 0.25 ± 0.02 | 0.28 ± 0.02 | 0.21 ± 0.02 | 0.043 ± 0.001 | 0.148 ± 0.001 | 89.12 ± 0.37 | 0.86 ± 0.15 |
LSTM | 0.14 ± 0.01 | 0.22 ± 0.01 | 0.24 ± 0.02 | 0.18 ± 0.01 | 0.037 ± 0.002 | 0.130 ± 0.001 | 90.41 ± 0.35 | 0.88 ± 0.17 |
IGWO-LSTM | 0.09 ± 0.01 | 0.15 ± 0.01 | 0.17 ± 0.01 | 0.12 ± 0.01 | 0.024 ± 0.001 | 0.072 ± 0.001 | 95.28 ± 0.28 | 0.93 ± 0.11 |
