Author Name AI technique used Objective of the research Advantages Limitation

in self-healing
E. Hossain [1] Machine Learning Fault detection, load forecasting, Learns from data, Needs large
(ML) predictive maintenance handles complexity, datasets, risk of
adaptable overfitting, less
interpretability
T. Sirojan [2] Deep Learning Image-based fault detection, High accuracy, handles High computation,
(DL) complex anomaly detection big/unstructured data, data-hungry, slow
scalable training
B. K. Bose [3] Expert Systems Rule-based fault diagnosis and Transparent decisions, Poor scalability,
restoration fast execution hard to adapt,
limited to
predefined rules
H. Shareef [4] Fuzzy Logic Handling uncertain data, load Deals with imprecision, Complex rule
Systems balancing decisions human-like logic, no design, performance
need for exact model depends on rules
M. R. Bishal [5] Artificial Neural Fault classification, power Good with nonlinear Needs tuning, prone
N. A. M. Leh [6] Networks (ANN) estimation, disturbance prediction data, fast inference post- to overfitting, hard
training to interpret
H. -M. Chung [7] Reinforcement Real-time control, adaptive Learns by interaction, Needs time to learn,
Learning (RL) decision-making, learning optimal adaptive, suited for reward system
strategies dynamic environments sensitive, unstable
during learning
Ashrafuzzaman Ensemble Learning Used for event detection by load Reduces overfitting Computationally
[8] changes over time, power flow High accuracy and intensive
anomalies robustness Requires feature
engineering and
tuning
A. Shahsavari [9] Micro PMU with Use labeled or unlabeled data to Identify disturbances like Data volume from
Machine Learning train models for anomaly faults, capacitor micro PMUs are
detection and classification switching, line trips very high, it needs
efficient processing
L. Zhang [10] K-Means / Unsupervised event clustering / DBSCAN filters noise Both K-means and
DBSCAN anomaly detection and identifies unique DBSCAN require
customer behaviors. Can careful tuning,
handle a variety of computational cost
datasets from smart is high
meters, making it
scalable for smart grid
applications.
M. Al Karim[11] SVM / Random Used for dynamic event detection Supports real-time Needs robust
Forest in a self-healing micro-grid activation of self-healing communication
(Events like short circuits, voltage mechanisms, Accurate among distributed
sags, equipment malfunctions, anomaly detection nodes
and cyber-attacks
B. Wang [174] LSTM achieve fast and accurate Quick Response, Requires a large
detection of abnormal or Pattern Recognition, volume of labeled
disruptive events in power Adaptive Learning training data.
systems (line trip, frequency Not always
deviation, cyber-attack) interpretable, that
limit operator trust
(Black box nature)
L. Guo [12] Deep Learning and Use the Discrete Wavelet High Accuracy, Computational Cost
Discrete Wavelet Transform to divide electrical Reduced Labeling is high,
Transform signals into multi-scale time- Effort, Performance is
frequency components, which Real-Time Compatible dependent on a
capture: varied and
Features include switching representative
events, harmonic content, and training dataset.
transient behaviours. High-frequency
noise may degrade
DWT performance
J. Barros [175] Decision Trees This method used to focus on Fast Response Time, Machine learning
automatically detecting and Reduces false alarms, models require
classifying voltage events large, labeled
datasets,
High-frequency
monitoring and real-
[1] E. Hossain, I. Khan, F. Un-Noor, S. S. Sikander and M. S. H. Sunny, "Application of Big Data and Machine
Learning in Smart Grid, and Associated Security Concerns: A Review," in IEEE Access, vol. 7, pp. 13960-13988,
2019, doi: 10.1109/ACCESS.2019.2894819.

[2] T. Sirojan, S. Lu, B. T. Phung, D. Zhang and E. Ambikairajah, "Sustainable Deep Learning at Grid Edge for
Real-Time High Impedance Fault Detection," in IEEE Transactions on Sustainable Computing, vol. 7, no. 2, pp.
346-357, 1 April-June 2022, doi: 10.1109/TSUSC.2018.2879960.

[3] B. K. Bose, "Artificial Intelligence Techniques in Smart Grid and Renewable Energy Systems—Some Example
Applications," in Proceedings of the IEEE, vol. 105, no. 11, pp. 2262-2273, Nov. 2017, doi:
10.1109/JPROC.2017.2756596.

[4] H. Shareef, M. S. Ahmed, A. Mohamed and E. Al Hassan, "Review on Home Energy Management System
Considering Demand Responses, Smart Technologies, and Intelligent Controllers," in IEEE Access, vol. 6, pp.
24498-24509, 2018, doi: 10.1109/ACCESS.2018.2831917.

[5] M. R. Bishal, S. Ahmed, N. M. Molla, K. M. Mamun, A. Rahman and M. A. A. Hysam, "ANN Based Fault
Detection & Classification in Power System Transmission line," 2021 International Conference on Science &
Contemporary Technologies (ICSCT), Dhaka, Bangladesh, 2021, pp. 1-4, doi: 10.1109/ICSCT53883.2021.9642410.
[6] N. A. M. Leh, F. M. Zain, Z. Muhammad, S. A. Hamid and A. D. Rosli, "Fault Detection Method Using ANN
for Power Transmission Line," 2020 10th IEEE International Conference on Control System, Computing and
Engineering (ICCSCE), Penang, Malaysia, 2020, pp. 79-84, doi: 10.1109/ICCSCE50387.2020.9204921.

[7] H. -M. Chung, S. Maharjan, Y. Zhang and F. Eliassen, "Distributed Deep Reinforcement Learning for Intelligent
Load Scheduling in Residential Smart Grids," in IEEE Transactions on Industrial Informatics, vol. 17, no. 4, pp.
2752-2763, April 2021, doi: 10.1109/TII.2020.3007167

[8] Ashrafuzzaman, Mohammad, et al. "Detecting stealthy false data injection attacks in the smart grid
using ensemble-based machine learning." Computers & Security 97 (2020): 101994.

[9] A. Shahsavari, M. Farajollahi, E. M. Stewart, E. Cortez and H. Mohsenian-Rad, "Situational Awareness in

Distribution Grid Using Micro-PMU Data: A Machine Learning Approach," in IEEE Transactions on Smart Grid,
vol. 10, no. 6, pp. 6167-6177, Nov. 2019, doi: 10.1109/TSG.2019.

[10] L. Zhang, S. Deng and S. Li, "Analysis of power consumer behavior based on the complementation of K-means
and DBSCAN," 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2), Beijing, China,
2017, pp. 1-5, doi: 10.1109/EI2.2017.8245490.

[11] M. Al Karim, J. Currie and T. -T. Lie, "Dynamic Event Detection Using a Distributed Feature Selection Based
Machine Learning Approach in a Self-Healing Microgrid," in IEEE Transactions on Power Systems, vol. 33, no. 5,
pp. 4706-4718, Sept. 2018, doi: 10.1109/TPWRS.2018.2812768.
[174] B. Wang, Y. Li and J. Yang, "LSTM-based Quick Event Detection in Power Systems," 2020 IEEE Power &
Energy Society General Meeting (PESGM), Montreal, QC, Canada, 2020, pp. 1-5, doi:
10.1109/PESGM41954.2020.9281569.

[12] L. Guo, S. Wang, H. Chen and Q. Shi, "A Load Identification Method Based on Active Deep Learning and
Discrete Wavelet Transform," in IEEE Access, vol. 8, pp. 113932-113942, 2020, doi:
10.1109/ACCESS.2020.3003778.
[175] J. Barros and E. Perez, "Automatic Detection and Analysis of Voltage Events in Power Systems," in IEEE
Transactions on Instrumentation and Measurement, vol. 55, no. 5, pp. 1487-1493, Oct. 2006, doi:
10.1109/TIM.2006.881584.