Table 1 Overview of the recent contributions.
Research topic | Dataset | Modeling technique | Performance | Researcher | Year |
|---|---|---|---|---|---|
Ensemble learning-based transmission line fault classification with explainable AI (XAI) | Multi-label | EXAI | 99.88% | 2024 | |
Microgrid Rotor Angle Stability via RFID Data and Deep Learning | Multi-label | CNN-LSTM | 99.88% | 2024 | |
Bayesian-optimized LSTM-DWT approach for reliable fault detection in MMC-based HVDC systems | Multi-label | LSTM-DWT | 99.04% | 2024 | |
Fault location and classification in power distribution systems | Binary-& Multilabel | WTO-CNN | 91.4% (detection) 94.93% (classification) | 2023 | |
Power system network’s fault classification and localization | Multi-label | XT | 97.53%(classification) 96.14%(localization) | 2023 | |
Transmission line fault detection and classification | Multi-label | LSTM | 99.00% 96.28–98.13% (without noise-with noise) | 2021 | |
Power quality disturbances dataset generator with reference classifiers | Multi-label | CNN BiLSTM | 99.28–99.75% (without noise-with noise) | 2021 | |
Transmission line fault detection and classification | Unlabeled | CNSF | CNSF97–99% (noise-high impedance) | 2021 | |
Power system network’s fault detection | Binary-label | SVM PCA | 79.84–79.28% | 2021 | |
Power system fault classification | Multi-label | DLA | 93.75–100% (dropout: 0.4–0.5) | 2021 | |
Power transformer fault diagnosis | Multi-label | EL | 90.61% | 2021 | |
Power distribution system fault classification | Unlabeled | MTLS-LR | 99.02% | 2021 | |
Power system fault classification | Multi-label | CNN | 99.27% | 2021 |
