Skip to main navigation Skip to search Skip to main content

Uncertainty-aware photovoltaic generation estimation through fusion of physics with harmonics information using Bayesian neural networks

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

5 Scopus citations

Abstract

We develop an aggregate photovoltaic generation estimation methodology that uses diverse inputs and can reason on its current input-dependent predictive uncertainty. Named PV-PHEst, for PhotoVoltaic Physics- & Harmonics-driven Estimator, the resulting tool is intelligently weighing and fusing information carried by the output of physics models, harmonics, and line sensors, using Bayesian neural networks and related techniques aimed at solving machine learning problems with intrinsic uncertainty quantification. As each of the three input classes carries heterogeneous information that only sheds light on one facet of the estimation problem but its value can diminish in the face of diverse grid phenomena, PV-PHEst with its estimation and uncertainty reasoning capabilities perform a nontrivial and potentially mission-critical task of value to grid operators.

Original languageEnglish
Title of host publication2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781665453554
ISBN (Print)9781665453554
DOIs
StatePublished - Mar 22 2023
Event2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023 - Washington, United States
Duration: Jan 16 2023Jan 19 2023

Publication series

Name2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023

Conference

Conference2023 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2023
Country/TerritoryUnited States
CityWashington
Period01/16/2301/19/23

Keywords

  • Analytics
  • Bayesian methods
  • Machine learning
  • Photovoltaic systems
  • Uncertainty quantification

INL Publication Number

  • INL/CON-23-71453
  • 150548

Fingerprint

Dive into the research topics of 'Uncertainty-aware photovoltaic generation estimation through fusion of physics with harmonics information using Bayesian neural networks'. Together they form a unique fingerprint.

Cite this