Physics-Informed Neural Networks in Grid-Connected Inverters: A Review

Mahdouri, Ekram Al; Al-Abri, Said; Yousef, Hassan; Al-Naimi, Ibrahim; Obeid, Hussein

doi:10.3390/en18205441

Open AccessReview

Physics-Informed Neural Networks in Grid-Connected Inverters: A Review

by

Ekram Al Mahdouri

^1,*,

Said Al-Abri

^1,*

,

Hassan Yousef

¹

,

Ibrahim Al-Naimi

¹

and

Hussein Obeid

²

¹

Department of Electrical and Computer Engineering, College of Engineering, Sultan Qaboos University, Muscat 123, Oman

²

Department of Mechanical and Industrial Engineering, College of Engineering, Sultan Qaboos University, Muscat 123, Oman

^*

Authors to whom correspondence should be addressed.

Energies 2025, 18(20), 5441; https://doi.org/10.3390/en18205441

Submission received: 6 September 2025 / Revised: 6 October 2025 / Accepted: 13 October 2025 / Published: 15 October 2025

(This article belongs to the Special Issue Integration of Energy Storage Technologies into Smart Grids and Modern Power Systems)

Download

Browse Figures

Versions Notes

Abstract

Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for modeling and controlling complex energy systems by embedding physical laws into deep learning architectures. This review paper highlights the application of PINNs in grid-connected inverter systems (GCISs), categorizing them by key tasks: parameter estimation, state estimation, control strategies, fault diagnosis and detection, and system identification. Particular focus is given to the use of PINNs in enabling accurate parameter estimation for aging and degradation monitoring. Studies show that PINN-based approaches can outperform purely data-driven models and traditional methods in both computational efficiency and accuracy. However, challenges remain, mainly related to high training costs and limited uncertainty quantification. To address these, emerging strategies such as advanced PINN frameworks are explored. The paper also explores emerging solutions and outlines future research directions to support the integration of PINNs into practical inverter design and operation.

Keywords: physics-informed neural networks; data-driven modeling; grid-connected inverters; parameter estimation; state estimation; control strategies; fault detection and diagnosis; system identification; smart grid

Share and Cite

MDPI and ACS Style

Mahdouri, E.A.; Al-Abri, S.; Yousef, H.; Al-Naimi, I.; Obeid, H. Physics-Informed Neural Networks in Grid-Connected Inverters: A Review. Energies 2025, 18, 5441. https://doi.org/10.3390/en18205441

AMA Style

Mahdouri EA, Al-Abri S, Yousef H, Al-Naimi I, Obeid H. Physics-Informed Neural Networks in Grid-Connected Inverters: A Review. Energies. 2025; 18(20):5441. https://doi.org/10.3390/en18205441

Chicago/Turabian Style

Mahdouri, Ekram Al, Said Al-Abri, Hassan Yousef, Ibrahim Al-Naimi, and Hussein Obeid. 2025. "Physics-Informed Neural Networks in Grid-Connected Inverters: A Review" Energies 18, no. 20: 5441. https://doi.org/10.3390/en18205441

APA Style

Mahdouri, E. A., Al-Abri, S., Yousef, H., Al-Naimi, I., & Obeid, H. (2025). Physics-Informed Neural Networks in Grid-Connected Inverters: A Review. Energies, 18(20), 5441. https://doi.org/10.3390/en18205441

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Physics-Informed Neural Networks in Grid-Connected Inverters: A Review

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI