Artificial Intelligence and Digital Twins for Fault Diagnosis and Predictive Maintenance in Renewable-Rich Power Systems

Dear Colleagues,

Power systems are moving toward high shares of renewable generation, inverter-based resources, distributed energy assets and data-intensive operation. Solar photovoltaic plants, wind farms, battery energy storage systems, electric vehicle charging stations, microgrids and smart distribution networks are now exposed to variable weather, bidirectional power flows, fast control actions and complex power–electronic interactions. These conditions change the behaviour of faults. Fault signatures may be weak, intermittent, nonlinear or hidden by load variation, environmental effects, converter switching, protection actions and communication delays.

Conventional methods, threshold-based alarms and fixed maintenance schedules remain useful. They are less attractive for systems with high renewable penetration and large numbers of monitored assets. Operators need earlier fault identification, clearer diagnosis, reliable asset health assessment and maintenance decisions based on real operating data. Artificial intelligence and digital twins offer a strong technical basis for this shift. Machine learning, deep learning, physics-informed models and hybrid methods can extract fault-related information from electrical, thermal, environmental and operational data. Digital twins can connect physical assets with virtual models, sensor streams, historical records and simulation-based decision support.

This Special Issue aims to publish high-quality research on artificial intelligence, digital twins, fault diagnosis, condition monitoring and predictive maintenance in renewable-rich power systems. Contributions may address new algorithms, modelling approaches, experimental platforms, real-time implementation, field data, benchmarking studies or critical reviews. Studies that combine data-driven methods with physical knowledge, power-system operation, power electronics and practical maintenance needs are particularly welcome.

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

• AI-based fault detection, diagnosis, localisation and classification in power systems;
• digital twins for condition monitoring and asset health assessment;
• predictive maintenance and remaining useful life estimation;
• fault diagnosis in PV systems, wind systems, batteries, EV chargers and microgrids;
• monitoring of inverters, converters, transformers, cables, protection devices and grid-connected assets;
• edge AI, IoT, SCADA, PMU and sensor-based monitoring;
• physics-informed and hybrid data-driven diagnostic models;
• explainable AI, graph neural networks, transfer learning and federated learning for power-system diagnostics;
• anomaly detection in renewable-rich and converter-dominated power systems;
• cyber–physical fault detection and attack-resilient monitoring;
• data quality, missing data, sensor faults, false-alarm reduction and multi-source data fusion;
• fault-tolerant control and maintenance-oriented decision support;
• real-time simulation, HIL/PHIL validation, open datasets and benchmarking.

Dr. Tariq Kamal
Dr. Syed Zulqadar Hassan
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. Electricity is an international peer-reviewed open access quarterly 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 1200 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.

• artificial intelligence
• digital twins
• fault diagnosis
• predictive maintenance
• condition monitoring
• renewable-rich power systems
• smart grids
• power electronics
• asset health management
• cyber–physical systems