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

Simon Stock*, Davood Babazadeh, Christian Becker, Spyros Chatzivasileiadis

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

21 Downloads (Pure)

Abstract

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%.
Original languageEnglish
Article number110860
JournalElectric Power Systems Research
Volume235
Number of pages10
ISSN0378-7796
DOIs
Publication statusPublished - 2024

Keywords

  • Bayesian physics-informed neural networks
  • System identification
  • Inverter-dominated power system
  • Machine learning

Fingerprint

Dive into the research topics of 'Bayesian Physics-informed Neural Networks for system identification of inverter-dominated power systems'. Together they form a unique fingerprint.

Cite this