Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems

Abdellahi Moulaye Rchid; Moussa Attia; Mohamed Elmamy MOHAMED MAHMOUD; Vatma Elvally; Zoubir Aoulmi; Abdelkader Ould Mahmoud

doi:10.51646/jsesd.v14i1.419

2026, Vol: 15, Issue: 1

15 / 1Current Issue Archive Aims and Scope Abstracting & Indexing Most Accessed Articles Most Downloaded Articles Most Cited Articles

« Previous Article

Technical Note
Online Published: 28 Apr 2025

Sol. Energy Sustain. Dev.. 2025; 14(1): 361-378

doi: 10.51646/jsesd.v14i1.419

Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems

Abdellahi Moulaye Rchid, Moussa Attia, Mohamed Elmamy Mohamed Mahmoud, Vatma Elvally, Zoubir Aoulmi, Abdelkader Ould Mahmoud.

Abstract
With the increasing adoption of solar photovoltaic (PV) systems, ensuring their reliability and efficiency is crucial for sustainable energy production. However, traditional fault detection methods rely on expensive manual inspections or sensor-based monitoring, often slow and inefficient. This study aims to bridge this gap by leveraging machine learning techniques to enhance fault detection and maintenance optimization in PV systems. We evaluate five advanced machine learning models—Random Forest, XGBoost, Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Support Vector Machines (SVM)—using accurate operational data from a 250-kW PV power station. The dataset includes key operational parameters such as current, voltage, power output, temperature, and irradiance. Data preprocessing included outlier removal, feature selection via Pearson correlation, and normalization to improve model performance. The models were trained and tested using an 80-20 data split and evaluated based on classification accuracy, precision, recall, and F1-score. Our results show that XGBoost achieved the highest accuracy (88%), making it the best candidate for real-time predictive maintenance. Random Forest also performed well (87% accuracy), particularly in handling noisy data. ANN and CNN models effectively detected long-term degradation patterns, supporting preventive maintenance strategies. Based on these findings, we propose a dual maintenance strategy: XGBoost and Random Forest for real-time fault detection, while ANN and CNN monitor gradual system deterioration. This research provides a practical framework for integrating machine learning techniques into PV system management, offering a scalable solution to enhance reliability, reduce maintenance costs, and optimize energy efficiency.

Key words: Photovoltaic systems, machine learning, fault detection, maintenance optimization, Renewable energy.

	ARTICLE TOOLS
	Abstract
	PDF Fulltext
	How to cite this article
	Citation Tools
	Related Records
	Articles by Abdellahi Moulaye Rchid Articles by Moussa Attia Articles by Mohamed Elmamy MOHAMED MAHMOUD Articles by Vatma Elvally Articles by Zoubir Aoulmi Articles by Abdelkader Ould Mahmoud
	on Google
	on Google Scholar

How to Cite this Article

Pubmed Style

Rchid AM, Attia M, Mahmoud MEM, Elvally V, Aoulmi Z, Mahmoud AO. Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems. Sol. Energy Sustain. Dev.. 2025; 14(1): 361-378.

doi:10.51646/jsesd.v14i1.419

Web Style

Rchid AM, Attia M, Mahmoud MEM, Elvally V, Aoulmi Z, Mahmoud AO. Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems. https://www.jsesd.org/?mno=302658351 [Access: November 12, 2026].

doi:10.51646/jsesd.v14i1.419

AMA (American Medical Association) Style

Rchid AM, Attia M, Mahmoud MEM, Elvally V, Aoulmi Z, Mahmoud AO. Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems. Sol. Energy Sustain. Dev.. 2025; 14(1): 361-378.

doi:10.51646/jsesd.v14i1.419

Vancouver/ICMJE Style

doi:10.51646/jsesd.v14i1.419

Harvard Style

Rchid, A. M., Attia, . M., Mahmoud, . M. E. M., Elvally, . V., Aoulmi, . Z. & Mahmoud, . A. O. (2025) Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems. Sol. Energy Sustain. Dev., 14 (1), 361-378.

doi:10.51646/jsesd.v14i1.419

Turabian Style

Rchid, Abdellahi Moulaye, Moussa Attia, Mohamed Elmamy Mohamed Mahmoud, Vatma Elvally, Zoubir Aoulmi, and Abdelkader Ould Mahmoud. 2025. Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems. Solar Energy and Sustainable Development, 14 (1), 361-378.

doi:10.51646/jsesd.v14i1.419

Chicago Style

Rchid, Abdellahi Moulaye, Moussa Attia, Mohamed Elmamy Mohamed Mahmoud, Vatma Elvally, Zoubir Aoulmi, and Abdelkader Ould Mahmoud. "Comparative Analysis of AI-Driven Machine Learning Models for Fault Detection and Maintenance Optimization in Photovoltaic Systems." Solar Energy and Sustainable Development 14 (2025), 361-378.

doi:10.51646/jsesd.v14i1.419

MLA (The Modern Language Association) Style

doi:10.51646/jsesd.v14i1.419

APA (American Psychological Association) Style

doi:10.51646/jsesd.v14i1.419

Author Login Reviewer Login About Publisher AI Policy

About Solar Energy and Sustainable Development

Contact Information

How to cite this article


About Solar Energy and Sustainable Development About the JournalThe Journal of Solar Energy and Sustainable Development (JSESD) is a peer-reviewed, open-access, biannual scientific journal dedicated to ... Read more. For best results, please use Internet Explorer or Google Chrome.	Contact Information