Verified physics-aware machine learning to transform non-linear power system stability and optimization

Informations projet

VeriPhIED

N° de convention de subvention: 949899

DOI

10.3030/949899

Date de signature de la CE 25 Août 2020

Date de début 1 Mai 2022

Date de fin 30 Avril 2027

Financé au titre de

• EXCELLENT SCIENCE - European Research Council (ERC)

Coût total

€ 1 499 183,00

Contribution de l’UE

€ 1 499 183,00

Coordonné par

DANMARKS TEKNISKE UNIVERSITET
Denmark

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Open Research Data Pilot (1)

Data Management Plan (DMP)

Participation in the Open Research Data Pilot

Publications

Peer reviewed articles (10)

Bayesian Physics-informed Neural Networks for system identification of inverter-dominated power systems

Auteurs: Simon Stock, Davood Babazadeh, Christian Becker, Spyros Chatzivasileiadis
Publié dans: Electric Power Systems Research, Numéro 235, 2024, Page(s) 110860, ISSN 0378-7796
Éditeur: Elsevier BV
DOI: 10.1016/j.epsr.2024.110860

Learning Active Constraints to Efficiently Solve Linear Bilevel Problems: Application to the Generator Strategic Bidding Problem

Auteurs: Eléa Prat, Spyros Chatzivasileiadis
Publié dans: IEEE Transactions on Power Systems, Numéro 38, 2024, Page(s) 2376-2387, ISSN 0885-8950
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpwrs.2022.3188432

Machine Learning in Power Systems: Is It Time to Trust It?

Auteurs: Spyros Chatzivasileiadis, Andreas Venzke, Jochen Stiasny, Georgios Misyris
Publié dans: IEEE Power and Energy Magazine, Numéro 20, 2022, Page(s) 32-41, ISSN 1540-7977
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/mpe.2022.3150810

Modeling the AC power flow equations with optimally compact neural networks: Application to unit commitment

Auteurs: Alyssa Kody, Samuel Chevalier, Spyros Chatzivasileiadis, Daniel Molzahn
Publié dans: Electric Power Systems Research, Numéro 213, 2024, Page(s) 108282, ISSN 0378-7796
Éditeur: Elsevier BV
DOI: 10.1016/j.epsr.2022.108282

PINNSim: A simulator for power system dynamics based on Physics-Informed Neural Networks

Auteurs: Jochen Stiasny, Baosen Zhang, Spyros Chatzivasileiadis
Publié dans: Electric Power Systems Research, Numéro 235, 2024, Page(s) 110796, ISSN 0378-7796
Éditeur: Elsevier BV
DOI: 10.1016/j.epsr.2024.110796

Can Machine Learning Help Keep the System Secure?: Power Systems and Change Addressing the Increasing Complexity and Uncertainty During the Energy Transition

Auteurs: Panagiotis N. Papadopoulos, Spyros Chatzivasileiadis, Antoine Marot
Publié dans: IEEE Power and Energy Magazine, Numéro 22, 2024, Page(s) 100-111, ISSN 1540-7977
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/mpe.2024.3421388

On Machine Learning-Based Techniques for Future Sustainable and Resilient Energy Systems

Auteurs: Jiawei Wang, Pierre Pinson, Spyros Chatzivasileiadis, Mathaios Panteli, Goran Strbac, Vladimir Terzija
Publié dans: IEEE Transactions on Sustainable Energy, Numéro 14, 2024, Page(s) 1230-1243, ISSN 1949-3029
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tste.2022.3194728

Physics-informed neural networks for phase locked loop transient stability assessment

Auteurs: Rahul Nellikkath, Ilgiz Murzakhanov, Spyros Chatzivasileiadis, Andreas Venzke, Mohammad Kazem Bakhshizadeh
Publié dans: Electric Power Systems Research, Numéro 236, 2024, Page(s) 110790, ISSN 0378-7796
Éditeur: Elsevier BV
DOI: 10.1016/j.epsr.2024.110790

Physics-Informed Neural Networks for AC Optimal Power Flow

Auteurs: Rahul Nellikkath, Spyros Chatzivasileiadis
Publié dans: Electric Power Systems Research, Numéro 212, 2024, Page(s) 108412, ISSN 0378-7796
Éditeur: Elsevier BV
DOI: 10.1016/j.epsr.2022.108412

Physics-informed neural networks for time-domain simulations: Accuracy, computational cost, and flexibility

Auteurs: Jochen Stiasny, Spyros Chatzivasileiadis
Publié dans: Electric Power Systems Research, Numéro 224, 2024, Page(s) 109748, ISSN 0378-7796
Éditeur: Elsevier BV
DOI: 10.1016/j.epsr.2023.109748

Other (3)

A Dataset Generation Toolbox for Dynamic Security Assessment: On the Role of the Security Boundary

Auteurs: Bastien Giraud, Lola Charles, Agnes Marjorie Nakiganda, Johanna Vorwerk, Spyros Chatzivasileiadis
Publié dans: 2025
Éditeur: Working Paper
DOI: 10.48550/arxiv.2501.09513

Minimizing Worst-Case Violations of Neural Networks

Auteurs: Nellikkath, Rahul; Chatzivasileiadis, Spyros
Publié dans: Numéro 2, 2022
Éditeur: Working Paper
DOI: 10.48550/arxiv.2212.10930

Correctness Verification of Neural Networks Approximating Differential Equations

Auteurs: Petros Ellinas, Rahul Nellikath, Ignasi Ventura, Jochen Stiasny, Spyros Chatzivasileiadis
Publié dans: Working Paper, 2024
Éditeur: ArXiV
DOI: 10.48550/arxiv.2402.07621

Conference proceedings (8)

Enriching Neural Network Training Dataset to Improve Worst-Case Performance Guarantees

Auteurs: Rahul Nellikkath, Spyros Chatzivasileiadis
Publié dans: 2023 IEEE Belgrade PowerTech, 2023, Page(s) 1-6
Éditeur: IEEE
DOI: 10.1109/powertech55446.2023.10202770

GPU-Accelerated Verification of Machine Learning Models for Power Systems

Auteurs: Samuel Chevalier, Ilgiz Murzakhanov, Spyros Chatzivasileiadis
Publié dans: Proceedings of the 57th Hawaii International Conference on System Sciences, 2024
Éditeur: IEEE

Bayesian Physics-Informed Neural Networks for Robust System Identification of Power Systems

Auteurs: Simon Stock, Jochen Stiasny, Davood Babazadeh, Christian Becker, Spyros Chatzivasileiadis
Publié dans: 2023 IEEE Belgrade PowerTech, 2023, Page(s) 1-6
Éditeur: IEEE
DOI: 10.1109/powertech55446.2023.10202692

Emission-Constrained Optimization of Gas Networks: Input-Convex Neural Network Approach

Auteurs: Vladimir Dvorkin, Samuel Chevalier, Spyros Chatzivasileiadis
Publié dans: 2023 62nd IEEE Conference on Decision and Control (CDC), 2024, Page(s) 1575-1579
Éditeur: IEEE
DOI: 10.1109/cdc49753.2023.10383948

Closing the Loop: A Framework for Trustworthy Machine Learning in Power Systems

Auteurs: Stiasny, Jochen; Chevalier, Samuel; Nellikkath, Rahul; Sævarsson, Brynjar; Chatzivasileiadis, Spyros
Publié dans: 2022 iREP Symposium - Bulk Power System Dynamics and Control - XI (iREP), Numéro 4, 2022
Éditeur: 11th Bulk Power Systems Dynamics and Control Symposium (IREP 2022)
DOI: 10.48550/arxiv.2203.07505

Neural Networks for Encoding Dynamic Security-Constrained Optimal Power Flow

Auteurs: Murzakhanov, Ilgiz; Venzke, Andreas; Misyris, George S.; Chatzivasileiadis, Spyros
Publié dans: Proceedings of 11th Bulk Power Systems Dynamics and Control Symposium, Numéro 5, 2022
Éditeur: IEEE
DOI: 10.48550/arxiv.2003.07939

Interpretable Machine Learning for Power Systems: Establishing Confidence in SHapley Additive exPlanations

Auteurs: Robert I. Hamilton, Jochen Stiasny, Tabia Ahmad, Samuel Chevalier, Rahul Nellikkath, Ilgiz Murzakhanov, Spyros Chatzivasileiadis, Panagiotis N. Papadopoulos
Publié dans: Climate Change Workshop of the International Conference on Learning Representations (ICLR), 2024
Éditeur: ICLR
DOI: 10.48550/arxiv.2209.05793

Accelerating Dynamical System Simulations with Contracting and Physics-Projected Neural-Newton Solvers

Auteurs: Samuel Chevalier, Jochen Stiasny, Spyros Chatzivasileiadis
Publié dans: Proceedings of Machine Learning Research, Numéro vol 168, 2022, Page(s) 1-14
Éditeur: 4th Annual Conference on Learning for Dynamics and Control