Physics-Informed AI and Deep Learning Algorithms for Smart Grid

Dear Colleagues,

The growing complexity and interconnectedness of smart grids demand advanced methodologies for ensuring efficient and reliable grid operations. The integration of renewable energy sources, the variability in energy demand, the link of power systems and transportation systems, and the need for robust grid management strategies underscore the necessity for sophisticated tools for the control and optimization of systems. Physics-informed artificial intelligence (AI) and deep learning algorithms represent a transformative approach to smart grid, vehicle to grid (V2G) system, and the key enablers—power electronics systems. These AI paradigms incorporate domain-specific knowledge—derived from physical laws and principles—into machine learning frameworks, resulting in more accurate, interpretable, and robust models, representing a combination of mathematical theory and computational innovation.

For instance, differential equations that characterize the energy dynamics within smart grid and the electrical–thermal–magnetic coupling effects in power electronics systems can be potentially solved by leveraging PINNs. Stochastic models combining PINNs can quantify the uncertainties and detect abnormal behaviors of systems in a confident manner. PINNs can facilitate the cyber–physical security, control, and optimization of systems. More examples will appear in the future.

This Special Issue aims to explore the cutting-edge physics-informed AI and deep learning algorithms tailored for smart grid, power electronics applications, and V2G technologies. By merging physics-based models with deep learning, researchers can overcome the limitations of purely data-driven approaches in terms of generalizability and explainability, particularly in scenarios where data are scarce or noisy. The manuscripts solicited for this Special Issue will focus on innovative research and practical applications that enhance grid performance, stability, and resilience and promote the life-cycle management of power electronics systems.

Dr. Xinze Li
Prof. Dr. Dongsheng Yu
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 100 words) can be sent to the Editorial Office for announcement on this website.

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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics 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.

• applications of physics-informed neural networks (PINNs) in smart grids
• AI-based control for system stability and reliability
• PINN and deep learning-based cyber security
• AI-based anomaly detection, forecasting, and scheduling for renewable energy generation
• PINN and deep learning-based distributed control for smart grid
• PINN-based modeling, control, and fault detection of power electronics systems
• AI-based fault detection and diagnostics in V2G system
• intelligent motor condition monitoring and fault-tolerant control for V2G system