Generative AI Applications for Power Systems

Dear Colleagues,

The digital transformation of modern power systems has led to the acquisition of vast amounts of data driven by the widespread deployment of smart metering and sensing technologies. This explosion of data has enabled advanced analytics using AI techniques to enhance the observability, operation, and planning of electrical grids, especially with the increasing penetration of renewable energy sources. Generative AI further leverages these developments by enabling a range of applications. These include the creation of realistic synthetic scenarios and data augmentation through Generative Adversarial Networks (GANs); probabilistic load and generation forecasting via Variational Autoencoders (VAEs); state estimation and reconstruction of missing data using input masking pretraining; simulation of rare or extreme events not captured in historical records through normalizing flows; and cross-domain situational awareness facilitated by multi-modal transformers.

In addition to these capabilities, generative AI is increasingly being used as an intelligent advisor, capable of synthesizing diverse data streams to provide contextual, real-time assessments of grid conditions. By continuously analyzing historical and live data, generative models can identify emerging patterns, predict abnormal system behavior, and suggest proactive mitigation strategies. This advisory role enhances operator situational awareness, supports risk-informed decision-making, and enables more agile responses to volatility introduced by renewable sources and demand-side flexibility activation.

With these capabilities, AI and generative AI empower utilities to perform more accurate forecasting, optimize grid operations, enhance reliability, and support the integration of renewables. Generative AI is now transitioning from traditional data augmentation and scenario generation toward real-time grid control, operator support, and market optimization. Continued interdisciplinary collaboration between electrical engineering, software engineering, and data science is essential to harness the full potential of these methods for power systems.

We look forward to your contributions.

Dr. Mònica Aragüés-Peñalba
Dr. Sara Barja-Martinez
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. AI is an international peer-reviewed open access monthly 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 1600 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.

• AI
• generative AI
• GANs
• VAEs
• transformers