Table 2.

Overview of review articles on ML and DL applications in photovoltaic (PV) systems (2016–2023)⁴⁰.

Authors	Year	Classification	ML models	PV system component	Contribution	Remarks
Youssef et al.41	2016	AI	ANN, FL, ANFIS, GA, GA-fuzzy, NN-fuzzy	PV field	Demonstrates the importance of AI in modeling, sizing, forecasting, and diagnosing faults in PV systems.	Compares the accuracy of different AI techniques with traditional methods, but does not specify the monitoring parameters for each method.
Daliento et al.42	2016	Electrical and AI	ANN, SVM, ANFIS, RBN	PV field	Provides a review of various methods used to monitor PV systems.	Well-written and adheres to desired characteristics; no changes were necessary.
Mellit et al.43	2016	Electrical and ML	ANN, FL, MSD	PV field	Discusses PV fault information and diagnosis methods.	Primarily focuses on identifying defects.
Rodrigues et al.44	2017	M.L.	DT, RF, FL, ANN, GA, Bayesian, KNN, GA-ANN, ANFIS, RVM, k-Means	PV field	Reviews prognosis and diagnosis of defects and covers the number of themes in the study.	Reviews types of studies, faults, input parameters, and PV systems but lacks evaluation of method effectiveness.
Madeti et al.45	2017	Conventional and AI	--	PV field	Reviews detection methods for grid-connected photovoltaic systems.	Already meets desired characteristics; no changes were made.
Mellit et al.46	2018	Electrical and ML	ANN, FL, GA, HS	PV field	Comprehensive review on detection methods for grid-connected PV systems.	Focuses on using electrical methods to diagnose faults.
Abdulmawjood et al.47	2018	Visual, Thermal, and ML Methods	SVM, k-Means, HMM, BN, ANN, GMM (Gaussian mixture model)	PV field	Covers different types of faults and detection techniques in PV fields.	Discussion is centered on electrical faults, but the detection parameters are not specified for each method.
Pillai et al.48	2018	IRT, ML, Others	ANN, LAPART	PV field	Includes a review of almost all PV faults and advanced detection techniques.	Focuses on flaws in detection methods.
Ghaffarzadeh et al.49	2019	Electric, ML	ANN, SVM, DT, FL, Kalman filter	PV field	Explains types of defects across a broad spectrum.	Focuses on current faults on the DC and AC sides of the PV system.
Appiah50	2019	IRF, ML, DL	ANN, LAPART, KELM, ANFIS	PV field	Reviews types of defects, their origins, and traditional and intelligent detection methods.	Clear and concise, but lacks complexity, precision, and input data.
Li et al.51	2020	M.L.	ANN	PV field	Focuses on ANN and hybrid methods applied to defect analysis, including data used, model configuration, and effectiveness.	Compares ANNs with other ML models, showing superiority of ANNs; however, does not compare between ANN models to identify the most efficient one.
Venkatesh et al.52	2020	Visual method, IRT, EL, ML	ANN, SVM, NC-NFC, CNN, DT, KNN, FL	PV field	Lists four types of visual defects and detection methods.	Does not take non-visual defects into account; lacks precision.
Kurukuru et al.53	2021	ML, DL	ANN, ANFIS, PSO, FL, GA, ABC, CNN, SVM, KNN, LSTM	PV field	Reviews the impact of AI on the PV value chain.	Does not provide precision for each technique.
Mansouri et al.54	2021	D.L.	DBN, CNN, RFCN, R-CNN	PV field	Reviews Deep Learning applications in solar cell fault detection.	Examines defects related to cell discoloration, cracking, and delamination in PV systems.
Abubakar et al.55	2021	AI, ML	ANN, SVM, LAPART, RBF-ELM, FL, GBSSL, ANFIS, DT	PV field	Discusses characteristics of AI methods, their speed, and effectiveness in detecting defects with minimal errors.	Does not justify inclusion of articles from the last 15 years; does not include accuracy rate for each model.
Gaviria et al.56	2022	D.L.	ANN, LSTM, CNN, SVM, RF	PV field	Reviews the interest of ML in PV systems, providing resources for datasets and source codes.	Lacks objectivity and precision in presenting results; includes insignificant articles on defect diagnosis using ML.
Hammoudi et al.57	2022	D.L.	CNN, LSTM	PV field	Surveys the interest of Deep Learning and IoT in PV system maintenance.	Limited to discussing deep learning in preventive maintenance on the DC side.
Zenebe et al.58	2022	ML, DL	SVM, DA, BN, ANN, KNN, RF, DT, CNN	PV field, Inverter	Reviews ML-based detection methods, showing that ANN and MLP are promising in terms of simplicity and accuracy.	Mainly focuses on defects and detection methods.
Yuan et al.59	2022	M.L.	ANN	PV field	Reviews progress of ANN in fault diagnosis.	Lacks information on precision and complexity of each ANN type.
Forootan et al.60	2022	ML, DL	SVM, DA, BN, ANN, kNN, RF, DT, CNN, FL, ANFIS, GA, LSTM, RL, MLR, SLR, k-Means, etc.	PV field	Reviews ML and DL algorithms in energy systems.	Fails to consider non-visual defects and lacks precision.
Berghout et al.61	2022	ML, DL	SVM, kNN, MLP, LSTM, CNN, Gans	PV field	Discusses monitoring PV systems and defects related to shading and degradation.	Focuses on ML categories, detection techniques, and two types of defects; does not provide accuracy for each model.
Puthiyapurayil et al.62	2022	AI, signal-based method	ANN, BPNN, SVM, CNN	Inverter	Lists different methods of diagnosing open-circuit faults in an NPC inverter.	Focuses only on single switch open-circuit faults; rare cases of three switch faults are not covered.
Engel et al.63	2022	ML, DL	ANN, CNN, ANFIS, YOLOv4, k-NN, DT, SVM, RF, NB	PV field	Reviews ML advances in prediction, forecasting, sizing, and diagnosis of PV systems.	Compares diagnostic methods, showing better performance of DNN models over non-neural models.
Ying-Yi et al.64	2022	Visual and thermal	SVM, kNN, MSD, DT, RF, ANFIS, ANN	PV field	Presents traditional methods of detecting and classifying PV faults and projects AI techniques.	Focuses on traditional methods but demonstrates potential of ML techniques.
Osmani et al.65	2023	Conventional methods, AI	SCADA, ANN, KELM (kernel extreme learning machine)	PV field	Critical review of detection methods in the PV field.	Presents DC and AC side faults, focusing on conventional methods and omitting supervised learning methods.
Islam et al.66	2023	Artificial intelligence based on ML and DL	AdaBoost, ANN, CNN, RNN, SVM, RF	PV field	Systematic review on identification and diagnosis methods, comparing existing reviews with its own in terms of technical approaches for fault detection.	Identifies most effective DL and ML approaches for PV fault diagnosis, showing DL’s superiority over conventional methods; does not provide accuracy rates for different methods.