Table 1 Relevant studies conducted using different ML-based approaches.
Analyzed aspects | Machine learning-based methods for different types of networks | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Proposed scheme | ||||||||||
Different parameters impact analysis | No (Load analysis) | No | No | No | No | No | No | No | No | Yes |
All fault types | No | Yes | Yes | Yes | Yes | Yes | Yes | Yes | No | Yes |
Imbalance system | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
Load variation | Yes | No | Yes | Yes | Yes | Yes | Yes | N/A | Yes | Yes |
Dynamic topology | No | No | No | Yes | Yes | No | Yes | N/A | Yes | Yes |
Grid connected/islanded mode | No | No | Yes | Yes | Yes | No | Yes | Yes | Yes | Yes |
Different O/C protection structure | No | No | No | No | No | No | No | No | No | Yes |
DGs variation impact | No | No | Yes | Yes | Yes | Yes | Yes | N/A | Yes | Yes |
High-impedance faults | Yes (HRF) | No | No | No | Yes | No | No | No | No | No |
