Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future Directions

With the rapid advancement of deep learning, generative artificial intelligence (Gen-AI) has emerged as a powerful tool, unlocking new prospects in the power systems sector. Despite the evident success of these methods and the rapid growth of this field in the power systems community, there is still...

Full description

Saved in:
Bibliographic Details
Main Authors: Elinor Ginzburg-Ganz, Eden Dina Horodi, Omar Shadafny, Uri Savir, Ram Machlev, Yoash Levron
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/10/2461
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126120251293696
author Elinor Ginzburg-Ganz
Eden Dina Horodi
Omar Shadafny
Uri Savir
Ram Machlev
Yoash Levron
author_facet Elinor Ginzburg-Ganz
Eden Dina Horodi
Omar Shadafny
Uri Savir
Ram Machlev
Yoash Levron
author_sort Elinor Ginzburg-Ganz
collection DOAJ
description With the rapid advancement of deep learning, generative artificial intelligence (Gen-AI) has emerged as a powerful tool, unlocking new prospects in the power systems sector. Despite the evident success of these methods and the rapid growth of this field in the power systems community, there is still a pressing need for a deeper understanding of how different evaluation metrics relate to the underlying statistical structure of the models. Another related important question is what tools can be used to quantify the different uncertainties, which are inherent in these problems, and stem not only from the physical system but also from the nature of the generative model itself. This paper attempts to address these challenges and provides a comprehensive review of existing evaluation metrics for generative models applied in various power system tasks. We analyze how these metrics align with the statistical properties of the models and explore their strengths and limitations. We also examine different sources of uncertainty, distinguishing between uncertainties inherent to the learning model, those arising from measurement errors, and other sources. Our general aim is to promote a better understanding of generative models as they are being applied in power systems to support this fascinating growing trend.
format Article
id doaj-art-2e059ff70e38424894eb93548802acb2
institution OA Journals
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-2e059ff70e38424894eb93548802acb22025-08-20T02:33:59ZengMDPI AGEnergies1996-10732025-05-011810246110.3390/en18102461Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future DirectionsElinor Ginzburg-Ganz0Eden Dina Horodi1Omar Shadafny2Uri Savir3Ram Machlev4Yoash Levron5The Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa 3200003, IsraelThe Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa 3200003, IsraelThe Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa 3200003, IsraelThe Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa 3200003, IsraelThe Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa 3200003, IsraelThe Andrew and Erna Viterbi Faculty of Electrical and Computer Engineering, Technion—Israel Institute of Technology, Haifa 3200003, IsraelWith the rapid advancement of deep learning, generative artificial intelligence (Gen-AI) has emerged as a powerful tool, unlocking new prospects in the power systems sector. Despite the evident success of these methods and the rapid growth of this field in the power systems community, there is still a pressing need for a deeper understanding of how different evaluation metrics relate to the underlying statistical structure of the models. Another related important question is what tools can be used to quantify the different uncertainties, which are inherent in these problems, and stem not only from the physical system but also from the nature of the generative model itself. This paper attempts to address these challenges and provides a comprehensive review of existing evaluation metrics for generative models applied in various power system tasks. We analyze how these metrics align with the statistical properties of the models and explore their strengths and limitations. We also examine different sources of uncertainty, distinguishing between uncertainties inherent to the learning model, those arising from measurement errors, and other sources. Our general aim is to promote a better understanding of generative models as they are being applied in power systems to support this fascinating growing trend.https://www.mdpi.com/1996-1073/18/10/2461generative modelspower systemsoptimal controluncertainty quantificationevaluation metricssmart grids
spellingShingle Elinor Ginzburg-Ganz
Eden Dina Horodi
Omar Shadafny
Uri Savir
Ram Machlev
Yoash Levron
Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future Directions
Energies
generative models
power systems
optimal control
uncertainty quantification
evaluation metrics
smart grids
title Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future Directions
title_full Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future Directions
title_fullStr Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future Directions
title_full_unstemmed Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future Directions
title_short Statistical Foundations of Generative AI for Optimal Control Problems in Power Systems: Comprehensive Review and Future Directions
title_sort statistical foundations of generative ai for optimal control problems in power systems comprehensive review and future directions
topic generative models
power systems
optimal control
uncertainty quantification
evaluation metrics
smart grids
url https://www.mdpi.com/1996-1073/18/10/2461
work_keys_str_mv AT elinorginzburgganz statisticalfoundationsofgenerativeaiforoptimalcontrolproblemsinpowersystemscomprehensivereviewandfuturedirections
AT edendinahorodi statisticalfoundationsofgenerativeaiforoptimalcontrolproblemsinpowersystemscomprehensivereviewandfuturedirections
AT omarshadafny statisticalfoundationsofgenerativeaiforoptimalcontrolproblemsinpowersystemscomprehensivereviewandfuturedirections
AT urisavir statisticalfoundationsofgenerativeaiforoptimalcontrolproblemsinpowersystemscomprehensivereviewandfuturedirections
AT rammachlev statisticalfoundationsofgenerativeaiforoptimalcontrolproblemsinpowersystemscomprehensivereviewandfuturedirections
AT yoashlevron statisticalfoundationsofgenerativeaiforoptimalcontrolproblemsinpowersystemscomprehensivereviewandfuturedirections