TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publications
  4. Bayesian Physics-informed Neural Networks for system identification of inverter-dominated power systems
 
Options

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

Citation Link: https://doi.org/10.15480/882.13170
Publikationstyp
Journal Article
Date Issued
2024-10
Sprache
English
Author(s)
Stock, Simon  orcid-logo
Elektrische Energietechnik E-6  
Babazadeh, Davood  orcid-logo
Electrical Power and Energy Technology E-6  
Becker, Christian  orcid-logo
Elektrische Energietechnik E-6  
Chatzivasileiadis, Spyros J.  
TORE-DOI
10.15480/882.13170
TORE-URI
https://hdl.handle.net/11420/48507
Journal
Electric power systems research  
Volume
235
Article Number
110860
Citation
Electric Power Systems Research 235: 110860 (2024)
Publisher DOI
10.1016/j.epsr.2024.110860
Scopus ID
2-s2.0-85198537323
Publisher
Elsevier
While the uncertainty in generation and demand increases, accurately estimating the dynamic characteristics of power systems becomes crucial for employing the appropriate control actions to maintain their stability. In our previous work, we have shown that Bayesian Physics-informed Neural Networks (BPINNs) outperform conventional system identification methods in identifying the power system dynamic behavior based on noisy data. This paper takes the next natural step and addresses the more significant challenge, exploring how BPINN performs in estimating power system dynamics under increasing uncertainty from many Inverter-based Resources (IBRs) connected to the grid. These introduce a different type of uncertainty, compared to noise. The BPINN combines the advantages of Physics-informed Neural Networks (PINNs), such as inverse problem applicability, with Bayesian approaches for uncertainty quantification. We explore the BPINN performance on a wide range of systems, starting from a single machine infinite bus (SMIB) system and 3-bus system to extract important insights, to the 14-bus CIGRE distribution grid, and the large IEEE 118-bus system. We also investigate approaches that can accelerate the BPINN training, such as pretraining and transfer learning. Throughout this paper, we show that in presence of uncertainty, the BPINN achieves orders of magnitude lower errors than the widely popular method for system identification SINDy and significantly lower errors than PINN, while transfer learning helps reduce training time by up to 75%.
Subjects
Bayesian Physics-informed Neural Networks
Inverter-dominated power systems
Machine learning
System identification
MLE@TUHH
DDC Class
621.3: Electrical Engineering, Electronic Engineering
Funding(s)
Projekt DEAL  
Publication version
publishedVersion
Lizenz
https://creativecommons.org/licenses/by/4.0/
Loading...
Thumbnail Image
Name

1-s2.0-S0378779624007466-main.pdf

Type

Main Article

Size

677.78 KB

Format

Adobe PDF

TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback