View in EDS HTML Full Text PDF Full Text

Integrating Machine Learning and AHP for Data-Driven Asset Renewal Prioritization in Power Distribution Systems.

Saved in:
Bibliographic Details
Title: Integrating Machine Learning and AHP for Data-Driven Asset Renewal Prioritization in Power Distribution Systems.
Authors: Santos, Igor M. A.1 (AUTHOR) igor.santos@ee.ufcg.edu.br, Vilar, Pablo B.1,2 (AUTHOR), Vieira, Breno A.1,3 (AUTHOR), Melo, João V. J. S.1,4 (AUTHOR), Galdino, Giovanny M. B.1 (AUTHOR), Leite Neto, Antonio F.1,2 (AUTHOR), Lira, George R. S.1,3 (AUTHOR), Sgotti, Virgínia A. C.2,4 (AUTHOR), Benítez, Ana G.3 (AUTHOR), Laube, Dirceu4 (AUTHOR), Macedo, Maycon R.4 (AUTHOR)
Source: Energies (19961073). Aug2026, Vol. 19 Issue 15, p3594. 32p.
Subject Terms: *Machine learning, *Analytic hierarchy process, *Statistical decision making, *Electric power distribution grids, *Condition-based maintenance, *Remaining useful life, *Electric power management
Abstract: This paper proposes an integrated framework for predictive asset management in electric power distribution systems by combining machine learning with the Analytic Hierarchy Process (AHP). Distinct utility datasets were used according to the characteristics of each prediction task. Annual preventive- and corrective-maintenance records, including maintenance cost and frequency, covered the period from 2016 to 2023, whereas the SAIDI and SAIFI annual time series covered the period from 2014 to 2023. Remaining Useful Life (RUL) estimation was based on static asset-level records from the entire available equipment stock and therefore was not associated with a single time-series interval. Multiple machine learning algorithms were evaluated independently for each Type of Utility Component (TUC), and the best-performing models were selected according to their validation errors. The resulting predictions were incorporated into a two-level AHP hierarchy that integrates technical, economic, operational, and regulatory criteria for portfolio-level asset-renewal prioritization. For RUL estimation, the selected TUC-specific models reduced the mean MAE from 11.33 years for the historical-mean baseline to 2.70 years, corresponding to an absolute improvement of 8.63 years and a relative reduction of 76.15%. The resulting priority ranking was evaluated retrospectively using moving-average, cumulative-gain, and lift analyses. The top 20% of ranked assets captured 29.61% of the observed corrective-maintenance occurrences, corresponding to a lift of 1.4806 relative to random selection. The cumulative-gain curve yielded an area under the curve of 0.6337 and a ranking Gini coefficient of 0.2674, indicating moderate positive discrimination across the asset portfolio. These results show that the proposed ML–AHP framework can support the allocation of inspection, engineering-assessment, and renewal resources toward assets with comparatively greater maintenance demand and operational relevance. The framework provides a structured, data-driven decision-support approach for utility asset-renewal planning, while prospective field implementation remains necessary to quantify reductions in failures, corrective maintenance, continuity penalties, and total expenditure. [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: 196241195
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Integrating Machine Learning and AHP for Data-Driven Asset Renewal Prioritization in Power Distribution Systems.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Santos%2C+Igor+M%2E+A%2E%22">Santos, Igor M. A.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> igor.santos@ee.ufcg.edu.br</i><br /><searchLink fieldCode="AR" term="%22Vilar%2C+Pablo+B%2E%22">Vilar, Pablo B.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Vieira%2C+Breno+A%2E%22">Vieira, Breno A.</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Melo%2C+João+V%2E+J%2E+S%2E%22">Melo, João V. J. S.</searchLink><relatesTo>1,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Galdino%2C+Giovanny+M%2E+B%2E%22">Galdino, Giovanny M. B.</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Leite+Neto%2C+Antonio+F%2E%22">Leite Neto, Antonio F.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lira%2C+George+R%2E+S%2E%22">Lira, George R. S.</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sgotti%2C+Virgínia+A%2E+C%2E%22">Sgotti, Virgínia A. C.</searchLink><relatesTo>2,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Benítez%2C+Ana+G%2E%22">Benítez, Ana G.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Laube%2C+Dirceu%22">Laube, Dirceu</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Macedo%2C+Maycon+R%2E%22">Macedo, Maycon R.</searchLink><relatesTo>4</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. Aug2026, Vol. 19 Issue 15, p3594. 32p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Analytic+hierarchy+process%22">Analytic hierarchy process</searchLink><br />*<searchLink fieldCode="DE" term="%22Statistical+decision+making%22">Statistical decision making</searchLink><br />*<searchLink fieldCode="DE" term="%22Electric+power+distribution+grids%22">Electric power distribution grids</searchLink><br />*<searchLink fieldCode="DE" term="%22Condition-based+maintenance%22">Condition-based maintenance</searchLink><br />*<searchLink fieldCode="DE" term="%22Remaining+useful+life%22">Remaining useful life</searchLink><br />*<searchLink fieldCode="DE" term="%22Electric+power+management%22">Electric power management</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper proposes an integrated framework for predictive asset management in electric power distribution systems by combining machine learning with the Analytic Hierarchy Process (AHP). Distinct utility datasets were used according to the characteristics of each prediction task. Annual preventive- and corrective-maintenance records, including maintenance cost and frequency, covered the period from 2016 to 2023, whereas the SAIDI and SAIFI annual time series covered the period from 2014 to 2023. Remaining Useful Life (RUL) estimation was based on static asset-level records from the entire available equipment stock and therefore was not associated with a single time-series interval. Multiple machine learning algorithms were evaluated independently for each Type of Utility Component (TUC), and the best-performing models were selected according to their validation errors. The resulting predictions were incorporated into a two-level AHP hierarchy that integrates technical, economic, operational, and regulatory criteria for portfolio-level asset-renewal prioritization. For RUL estimation, the selected TUC-specific models reduced the mean MAE from 11.33 years for the historical-mean baseline to 2.70 years, corresponding to an absolute improvement of 8.63 years and a relative reduction of 76.15%. The resulting priority ranking was evaluated retrospectively using moving-average, cumulative-gain, and lift analyses. The top 20% of ranked assets captured 29.61% of the observed corrective-maintenance occurrences, corresponding to a lift of 1.4806 relative to random selection. The cumulative-gain curve yielded an area under the curve of 0.6337 and a ranking Gini coefficient of 0.2674, indicating moderate positive discrimination across the asset portfolio. These results show that the proposed ML–AHP framework can support the allocation of inspection, engineering-assessment, and renewal resources toward assets with comparatively greater maintenance demand and operational relevance. The framework provides a structured, data-driven decision-support approach for utility asset-renewal planning, while prospective field implementation remains necessary to quantify reductions in failures, corrective maintenance, continuity penalties, and total expenditure. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=196241195
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19153594
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 32
        StartPage: 3594
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Analytic hierarchy process
        Type: general
      – SubjectFull: Statistical decision making
        Type: general
      – SubjectFull: Electric power distribution grids
        Type: general
      – SubjectFull: Condition-based maintenance
        Type: general
      – SubjectFull: Remaining useful life
        Type: general
      – SubjectFull: Electric power management
        Type: general
    Titles:
      – TitleFull: Integrating Machine Learning and AHP for Data-Driven Asset Renewal Prioritization in Power Distribution Systems.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Santos, Igor M. A.
      – PersonEntity:
          Name:
            NameFull: Vilar, Pablo B.
      – PersonEntity:
          Name:
            NameFull: Vieira, Breno A.
      – PersonEntity:
          Name:
            NameFull: Melo, João V. J. S.
      – PersonEntity:
          Name:
            NameFull: Galdino, Giovanny M. B.
      – PersonEntity:
          Name:
            NameFull: Leite Neto, Antonio F.
      – PersonEntity:
          Name:
            NameFull: Lira, George R. S.
      – PersonEntity:
          Name:
            NameFull: Sgotti, Virgínia A. C.
      – PersonEntity:
          Name:
            NameFull: Benítez, Ana G.
      – PersonEntity:
          Name:
            NameFull: Laube, Dirceu
      – PersonEntity:
          Name:
            NameFull: Macedo, Maycon R.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: Aug2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 15
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1