Table 1 State of the art of voltage stability detection
References | Year | Method | Stability detection | Critical Bus detection | PV Integration | Stability Type | input | Test case | Performance |
|---|---|---|---|---|---|---|---|---|---|
Yari and Khoshkhoo (2017) | 2017 | Lmn, FVSI, LQP and NVSI | ✓ | – | – | Long-Term Voltage | Z, X, P, Q, V, θ, δ | 9 bus | – |
Zhou et al. (2010) | 2010 | ANN | ✓ | – | – | Long-Term Voltage | P, Q, V, θ | 39 bus | Mean error: 0.1205–0.6528% Maximum error: 0.6566–2.2614% |
Ashraf et al. (2017) | 2017 | ANN | ✓ | – | – | Long-Term Voltage | P, Q and/or V, θ | 14 bus, 118 bus | Maximum error: 0.055–0.4916% |
Pérez-Londoño et al. (2017) | 2017 | SVM | ✓ | ✓ | – | Long-Term Voltage | V, P, Q | 14 bus, and 30 bus | Accuracy: 99.9% |
Nandanwar et al. (2018) | 2018 | PFDT and CBR | ✓ | – | – | Long-Term Voltage | P, Q | 30 bus | Accuracy: 94% |
Su and Liu (2018) | 2018 | Random Forest | ✓ | – | – | Long-Term Voltage | P, Q, V, θ | 57 bus, Taiwan Power System (1821 bus) | Accuracy: 94.8–99.9% |
Pinzón and Colomé (2019) | 2019 | Random Forest | ✓ | – | – | Short-Term Voltage | V | 39 bus | Mean error: 1.697–2.033% |
Adhikari et al. (2020) | 2020 | Gaussian Process Regression, ANN, SVM, DT | ✓ | – | – | Long-Term Voltage | V, θ | 39 bus | MSE: 0.568–14.37% |
Dharmapala et al. (2020) | 2020 | Random Forest | ✓ | – | – | Long-Term Voltage | Z, P, Q, V, θ, δ | 14 bus, 118 bus | RMSE: 0.61–5.07% |
Mollaiee et al. (2021) | 2021 | DT, SVM, AdaBoost, Bagged Tree | ✓ | – | – | Long-Term Voltage | P, Q, V, θ | 39 bus, 118 bus | Accuracy: 69–96.02% |
Rizvi et al. (2021) | 2021 | 1D-CNN | ✓ | ✓ | – | Short-Term Voltage | V | 30 bus, 39 bus, 118 bus | Accuracy: 92–100% |
Proposed | 2023 | ANN | ✓ | ✓ | ✓ | Long-Term Voltage | V, θ | 14 bus | Accuracy: > 96% |