go-v.orgdoi

A Genetic Algorithm Based Methodology for Prioritizing Maintenance Actions of Power Distribution Utilities

Danilo de Souza Pereira, Carlos Frederico Meschini Almeida, Nelson Kagan, Marcos Roberto Gouvêa, Junior, José, Junior, James, Fabrício Viana, Alexandre Dominice · CIRED · 2019

  • DOI 10.34890/583
  • Publisher CIRED
  • Type article
  • Issued 2019

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

CIRED · CIRED · article · 2019

Abstract

Yearly, power distribution utilities plan preventive maintenance actions, aiming at reducing durations and frequencies of power outages. Currently, utilities planning engineers prioritize maintenance actions based on multiple spreadsheets, personal experience and cumbersome procedures. Typically, they simply rank the actions according to their expected benefits. Then a set of actions is selected depending on their costs and on the budgets available. This paper proposes a Genetic Algorithm (GA)-based methodology which provides an optimal plan of maintenance actions considering the financial restrictions.

Four major types of actions are addressed, regarding the targeted assets: general Medium Voltage (MV) equipment, general Low Voltage (LV) equipment, MV/LV transformers and poles. To apply the proposed methodology, a case study was set up considering a Brazilian power distribution area. By executing the methodology for each of the four major types of actions, a plan of optimal maintenance actions was produced, considering the corresponding budget restrictions. The methodology succeeded in providing an optimal plan of suitable actions for a real power distribution substation.

Open the resolved locator · 10.34890/583

Metadata licence: OpenAlex metadata (CC0)

Registry
OpenAlex DOI index + API
Fetched
2026-11-20 00:35 UTC
Cache state
not cached yet (bulk-index+openalex)
Locator
https://doi.org/10.34890/583
Metadata licence
OpenAlex metadata (CC0)
Scope
Metadata as returned by the resolver; abstracts are never generated here.