Convolutional Neural Network-based Inertia Estimation using Local Frequency Measurements

Abodh Poudyal, Robert Fourney, Reinaldo Tonkoski, Timothy M. Hansen, Ujjwol Tamrakar, Rodrigo D. Trevizan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

16 Scopus citations

Abstract

Increasing installation of renewable energy resources makes the power system inertia a time-varying quantity. Furthermore, converter-dominated grids have different dynamics compared to conventional grids and therefore estimates of the inertia constant using existing dynamic power system models are unsuitable. In this paper, a novel inertia estimation technique based on convolutional neural networks that use local frequency measurements is proposed. The model uses a non-intrusive excitation signal to perturb the system and measure frequency using a phase-locked loop. The estimated inertia constants, within 10% of actual values, have an accuracy of 97.35% and root mean square error of 0.2309. Furthermore, the model evaluated on unknown frequency measurements during the testing phase estimated the inertia constant with a root mean square error of 0.1763. The proposed model-free approach can estimate the inertia constant with just local frequency measurements and can be applied over traditional inertia estimation methods that do not incorporate the dynamic impact of renewable energy sources.

Original languageEnglish
Title of host publication2020 52nd North American Power Symposium, NAPS 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728181929
DOIs
StatePublished - 11 Apr 2021
Externally publishedYes
Event52nd North American Power Symposium, NAPS 2020 - Tempe, United States
Duration: 11 Apr 202113 Apr 2021

Publication series

Name2020 52nd North American Power Symposium, NAPS 2020

Conference

Conference52nd North American Power Symposium, NAPS 2020
Country/TerritoryUnited States
CityTempe
Period11/04/2113/04/21

Keywords

  • Convolutional neural network
  • frequency measurements
  • inertia estimation
  • low inertia grids

Fingerprint

Dive into the research topics of 'Convolutional Neural Network-based Inertia Estimation using Local Frequency Measurements'. Together they form a unique fingerprint.

Cite this