Advanced Methods for Performance Monitoring of Photovoltaic Systems: Artificial Intelligence, Physics-Based, and Hybrid Approaches

Dear Colleagues,

Photovoltaic (PV) solar energy is leading the growth of newly installed power generation capacity worldwide, driven by its continuously decreasing levelized cost of energy (LCOE) and its increasingly important role in the global energy transition.

As PV generation becomes a critical component of modern power systems, ensuring the reliability, safety, and long-term performance of PV assets is becoming more important than ever. However, the continuous pressure to reduce LCOE is accelerating the deployment of new PV technologies that often have limited operational track records. As a result, some recently commissioned PV plants are experiencing higher-than-expected degradation rates.

The development of advanced methodologies for the detection and identification of failure modes has therefore become essential for improving the reliability, efficiency, and bankability of PV systems. Beyond supporting operation and maintenance activities, these methodologies can also provide valuable feedback throughout the PV value chain, helping manufacturers, developers, and asset owners to identify technologies, materials, and designs choices to avoid premature failures.

In this context, advanced methods based on artificial intelligence (AI) are enabling a better performance assessment, energy forecasting, anomaly detection and diagnosis, and predictive maintenance. Particularly promising are approaches that combine the strengths of physical and expert knowledge with data-driven learning. Physics-informed machine learning, hybrid models, digital twins and explainable AI are creating new opportunities for more resilient and trustworthy PV systems.

These advances are being boosted by the unprecedented availability of operational data in new PV installations. High-frequency SCADA systems, string-level and module-level monitoring, smart sensors, and imaging inspection techniques such as infrared thermography or electroluminescence (EL) are contributing to generating large and more diverse datasets.

This Special Issue aims to gather high-quality original research and review articles addressing advanced methodologies for performance monitoring in PV systems based on AI, machine learning (ML), physics-based modeling, digital twins and hybrid approaches. Although particular emphasis is placed on failure detection and diagnosis, contributions addressing broader applications like forecasting, degradation analysis, and operational optimization are also welcome.

Topics of interest include, but are not limited to the following:

- PV systems and new PV module technologies;

- AI and ML for PV application;

- Physics-based, data-driven, and hybrid modeling;

- Physics-informed machine learning;

- Digital twins for PV systems;

- Fault detection and diagnosis;

- Predictive maintenance and reliability assessment;

- Degradation analysis and lifetime prediction;

- Energy yield assessment and forecasting;

- Analysis of SCADA data and I-V curves;

- Analysis of imaging data (IR thermography, electroluminescence, visual imaging);

Although this Special Issue covers interdisciplinary research, the core focus of all submissions must remain within the field of photovoltaic solar energy.

Dr. Jose Domingo Santos Rodriguez
Dr. Sergio Gil-Lopez
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Energies is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• photovoltaic systems
• solar photovoltaics
• pv reliability
• performance monitoring
• artificial intelligence (AI)
• machine learning (ML)
• physics-Informed machine learning
• hybrid modeling
• physics-based modeling
• digital twins
• fault detection and diagnosis (FDD)
• predictive maintenance
• degradation analysis
• lifetime prediction
• anomaly detection
• energy yield assessment
• PV forecasting
• SCADA analytics
• I-V curve modeling
• infrared thermography
• electroluminescence
• visual imaging
• multimodal data fusion