View in EDS HTML Full Text PDF Full Text

Data-Driven Probabilistic Forecasting of Voltage Quality in Distribution Transformers Using Gaussian Processes.

Saved in:
Bibliographic Details
Title: Data-Driven Probabilistic Forecasting of Voltage Quality in Distribution Transformers Using Gaussian Processes.
Authors: Mondragón-García, Efraín1 (AUTHOR), Jesús, Ángel Marroquín de1,2 (AUTHOR), García-García, Raúl1,3 (AUTHOR), Salazar-Flores, Yuri2,4 (AUTHOR), Díaz-Hernández, Adán1,3 (AUTHOR), Vallejo-Castañeda, Emmanuel2,4 (AUTHOR) emmanuel_vallejo@uaeh.edu.mx
Source: Energies (19961073). May2026, Vol. 19 Issue 9, p2133. 37p.
Subject Terms: *Gaussian processes, *Forecasting, *Time series analysis, *Prediction models, *Power supply quality, *Power transformers, *Covariance matrices, *Uncertainty (Information theory)
Abstract: A probabilistic data-driven framework for voltage quality forecasting in distribution transformers based on Gaussian process regression and high-resolution field measurements is presented. Voltage time series acquired under real operating conditions were modeled using composite covariance functions designed to capture long-term trends and stochastic multi-scale fluctuations. The proposed approach enables simultaneous prediction and uncertainty quantification, allowing direct compliance assessment with voltage quality standards. The additive Gaussian process models achieved coefficients of determination above 0.75 and produced statistically uncorrelated residuals, indicating an adequate representation of the intrinsic temporal structure. However, the predictive intervals exhibit a certain level of undercoverage, indicating that, while uncertainty is effectively quantified, there is still room for improvement in calibration. The selected kernel structures revealed distinct physical regimes in the voltage dynamics, including smooth steady operation, moderately irregular behavior associated with localized disturbances, and multi-scale stochastic variability. For benchmarking purposes, results were compared with those obtained from a stochastic damped harmonic oscillator with restoring force, a naive model, a seasonal naive model and an Autoregressive Integrated Moving Average model. The oscillator model, the naive model, the seasonal naive model, and the Autoregressive Integrated Moving Average model generated strongly autocorrelated residuals, whereas the Gaussian process models yielded consistent white-noise residuals that outperformed all the other models. These findings demonstrate that probabilistic Gaussian process modeling provides an interpretable, scalable, and uncertainty-aware alternative for predictive voltage quality assessment in modern distribution systems. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 193716029
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Data-Driven Probabilistic Forecasting of Voltage Quality in Distribution Transformers Using Gaussian Processes.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Mondragón-García%2C+Efraín%22">Mondragón-García, Efraín</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Jesús%2C+Ángel+Marroquín+de%22">Jesús, Ángel Marroquín de</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22García-García%2C+Raúl%22">García-García, Raúl</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Salazar-Flores%2C+Yuri%22">Salazar-Flores, Yuri</searchLink><relatesTo>2,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Díaz-Hernández%2C+Adán%22">Díaz-Hernández, Adán</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Vallejo-Castañeda%2C+Emmanuel%22">Vallejo-Castañeda, Emmanuel</searchLink><relatesTo>2,4</relatesTo> (AUTHOR)<i> emmanuel_vallejo@uaeh.edu.mx</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. May2026, Vol. 19 Issue 9, p2133. 37p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Gaussian+processes%22">Gaussian processes</searchLink><br />*<searchLink fieldCode="DE" term="%22Forecasting%22">Forecasting</searchLink><br />*<searchLink fieldCode="DE" term="%22Time+series+analysis%22">Time series analysis</searchLink><br />*<searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br />*<searchLink fieldCode="DE" term="%22Power+supply+quality%22">Power supply quality</searchLink><br />*<searchLink fieldCode="DE" term="%22Power+transformers%22">Power transformers</searchLink><br />*<searchLink fieldCode="DE" term="%22Covariance+matrices%22">Covariance matrices</searchLink><br />*<searchLink fieldCode="DE" term="%22Uncertainty+%28Information+theory%29%22">Uncertainty (Information theory)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: A probabilistic data-driven framework for voltage quality forecasting in distribution transformers based on Gaussian process regression and high-resolution field measurements is presented. Voltage time series acquired under real operating conditions were modeled using composite covariance functions designed to capture long-term trends and stochastic multi-scale fluctuations. The proposed approach enables simultaneous prediction and uncertainty quantification, allowing direct compliance assessment with voltage quality standards. The additive Gaussian process models achieved coefficients of determination above 0.75 and produced statistically uncorrelated residuals, indicating an adequate representation of the intrinsic temporal structure. However, the predictive intervals exhibit a certain level of undercoverage, indicating that, while uncertainty is effectively quantified, there is still room for improvement in calibration. The selected kernel structures revealed distinct physical regimes in the voltage dynamics, including smooth steady operation, moderately irregular behavior associated with localized disturbances, and multi-scale stochastic variability. For benchmarking purposes, results were compared with those obtained from a stochastic damped harmonic oscillator with restoring force, a naive model, a seasonal naive model and an Autoregressive Integrated Moving Average model. The oscillator model, the naive model, the seasonal naive model, and the Autoregressive Integrated Moving Average model generated strongly autocorrelated residuals, whereas the Gaussian process models yielded consistent white-noise residuals that outperformed all the other models. These findings demonstrate that probabilistic Gaussian process modeling provides an interpretable, scalable, and uncertainty-aware alternative for predictive voltage quality assessment in modern distribution systems. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=193716029
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19092133
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 37
        StartPage: 2133
    Subjects:
      – SubjectFull: Gaussian processes
        Type: general
      – SubjectFull: Forecasting
        Type: general
      – SubjectFull: Time series analysis
        Type: general
      – SubjectFull: Prediction models
        Type: general
      – SubjectFull: Power supply quality
        Type: general
      – SubjectFull: Power transformers
        Type: general
      – SubjectFull: Covariance matrices
        Type: general
      – SubjectFull: Uncertainty (Information theory)
        Type: general
    Titles:
      – TitleFull: Data-Driven Probabilistic Forecasting of Voltage Quality in Distribution Transformers Using Gaussian Processes.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Mondragón-García, Efraín
      – PersonEntity:
          Name:
            NameFull: Jesús, Ángel Marroquín de
      – PersonEntity:
          Name:
            NameFull: García-García, Raúl
      – PersonEntity:
          Name:
            NameFull: Salazar-Flores, Yuri
      – PersonEntity:
          Name:
            NameFull: Díaz-Hernández, Adán
      – PersonEntity:
          Name:
            NameFull: Vallejo-Castañeda, Emmanuel
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1