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

Informazioni relative al progetto

VeriPhIED

ID dell’accordo di sovvenzione: 949899

DOI

10.3030/949899

Data della firma CE 25 Agosto 2020

Data di avvio 1 Maggio 2022

Data di completamento 30 Aprile 2027

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 499 183,00

Contributo UE

€ 1 499 183,00

Coordinato da

DANMARKS TEKNISKE UNIVERSITET
Denmark

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Open Research Data Pilot (1)

Data Management Plan (DMP)

Participation in the Open Research Data Pilot

Pubblicazioni

Peer reviewed articles (10)

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

Autori: Simon Stock, Davood Babazadeh, Christian Becker, Spyros Chatzivasileiadis
Pubblicato in: Electric Power Systems Research, Numero 235, 2024, Pagina/e 110860, ISSN 0378-7796
Editore: 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

Autori: Eléa Prat, Spyros Chatzivasileiadis
Pubblicato in: IEEE Transactions on Power Systems, Numero 38, 2024, Pagina/e 2376-2387, ISSN 0885-8950
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tpwrs.2022.3188432

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

Autori: Spyros Chatzivasileiadis, Andreas Venzke, Jochen Stiasny, Georgios Misyris
Pubblicato in: IEEE Power and Energy Magazine, Numero 20, 2022, Pagina/e 32-41, ISSN 1540-7977
Editore: 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

Autori: Alyssa Kody, Samuel Chevalier, Spyros Chatzivasileiadis, Daniel Molzahn
Pubblicato in: Electric Power Systems Research, Numero 213, 2024, Pagina/e 108282, ISSN 0378-7796
Editore: Elsevier BV
DOI: 10.1016/j.epsr.2022.108282

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

Autori: Jochen Stiasny, Baosen Zhang, Spyros Chatzivasileiadis
Pubblicato in: Electric Power Systems Research, Numero 235, 2024, Pagina/e 110796, ISSN 0378-7796
Editore: 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

Autori: Panagiotis N. Papadopoulos, Spyros Chatzivasileiadis, Antoine Marot
Pubblicato in: IEEE Power and Energy Magazine, Numero 22, 2024, Pagina/e 100-111, ISSN 1540-7977
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/mpe.2024.3421388

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

Autori: Jiawei Wang, Pierre Pinson, Spyros Chatzivasileiadis, Mathaios Panteli, Goran Strbac, Vladimir Terzija
Pubblicato in: IEEE Transactions on Sustainable Energy, Numero 14, 2024, Pagina/e 1230-1243, ISSN 1949-3029
Editore: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tste.2022.3194728

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

Autori: Rahul Nellikkath, Ilgiz Murzakhanov, Spyros Chatzivasileiadis, Andreas Venzke, Mohammad Kazem Bakhshizadeh
Pubblicato in: Electric Power Systems Research, Numero 236, 2024, Pagina/e 110790, ISSN 0378-7796
Editore: Elsevier BV
DOI: 10.1016/j.epsr.2024.110790

Physics-Informed Neural Networks for AC Optimal Power Flow

Autori: Rahul Nellikkath, Spyros Chatzivasileiadis
Pubblicato in: Electric Power Systems Research, Numero 212, 2024, Pagina/e 108412, ISSN 0378-7796
Editore: Elsevier BV
DOI: 10.1016/j.epsr.2022.108412

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

Autori: Jochen Stiasny, Spyros Chatzivasileiadis
Pubblicato in: Electric Power Systems Research, Numero 224, 2024, Pagina/e 109748, ISSN 0378-7796
Editore: 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

Autori: Bastien Giraud, Lola Charles, Agnes Marjorie Nakiganda, Johanna Vorwerk, Spyros Chatzivasileiadis
Pubblicato in: 2025
Editore: Working Paper
DOI: 10.48550/arxiv.2501.09513

Minimizing Worst-Case Violations of Neural Networks

Autori: Nellikkath, Rahul; Chatzivasileiadis, Spyros
Pubblicato in: Numero 2, 2022
Editore: Working Paper
DOI: 10.48550/arxiv.2212.10930

Correctness Verification of Neural Networks Approximating Differential Equations

Autori: Petros Ellinas, Rahul Nellikath, Ignasi Ventura, Jochen Stiasny, Spyros Chatzivasileiadis
Pubblicato in: Working Paper, 2024
Editore: ArXiV
DOI: 10.48550/arxiv.2402.07621

Conference proceedings (8)

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

Autori: Rahul Nellikkath, Spyros Chatzivasileiadis
Pubblicato in: 2023 IEEE Belgrade PowerTech, 2023, Pagina/e 1-6
Editore: IEEE
DOI: 10.1109/powertech55446.2023.10202770

GPU-Accelerated Verification of Machine Learning Models for Power Systems

Autori: Samuel Chevalier, Ilgiz Murzakhanov, Spyros Chatzivasileiadis
Pubblicato in: Proceedings of the 57th Hawaii International Conference on System Sciences, 2024
Editore: IEEE

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

Autori: Simon Stock, Jochen Stiasny, Davood Babazadeh, Christian Becker, Spyros Chatzivasileiadis
Pubblicato in: 2023 IEEE Belgrade PowerTech, 2023, Pagina/e 1-6
Editore: IEEE
DOI: 10.1109/powertech55446.2023.10202692

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

Autori: Vladimir Dvorkin, Samuel Chevalier, Spyros Chatzivasileiadis
Pubblicato in: 2023 62nd IEEE Conference on Decision and Control (CDC), 2024, Pagina/e 1575-1579
Editore: IEEE
DOI: 10.1109/cdc49753.2023.10383948

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

Autori: Stiasny, Jochen; Chevalier, Samuel; Nellikkath, Rahul; Sævarsson, Brynjar; Chatzivasileiadis, Spyros
Pubblicato in: 2022 iREP Symposium - Bulk Power System Dynamics and Control - XI (iREP), Numero 4, 2022
Editore: 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

Autori: Murzakhanov, Ilgiz; Venzke, Andreas; Misyris, George S.; Chatzivasileiadis, Spyros
Pubblicato in: Proceedings of 11th Bulk Power Systems Dynamics and Control Symposium, Numero 5, 2022
Editore: IEEE
DOI: 10.48550/arxiv.2003.07939

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

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

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

Autori: Samuel Chevalier, Jochen Stiasny, Spyros Chatzivasileiadis
Pubblicato in: Proceedings of Machine Learning Research, Numero vol 168, 2022, Pagina/e 1-14
Editore: 4th Annual Conference on Learning for Dynamics and Control