Sage Journals: Discover world-class research

Abstract

As public power grids expand, utility providers face increasing challenges in managing vast inventories of infrastructure assets. Effective asset prioritization and disposal planning are critical to maintaining system reliability, minimizing operational risks, and optimizing financial performance. This research introduces a robust data-driven framework for asset prioritization and disposal planning by integrating advanced analytics and optimization techniques. Diverse datasets are collected, including asset condition reports, maintenance logs, operational performance data, failure records, and environmental parameters. Data preprocessing uses Z-score normalization to scale numerical features and handle anomalies, while missing values are treated using appropriate imputation methods to maintain dataset integrity. Asset prioritization is assessed using the Analytic Hierarchy Process (AHP), enabling structured multi-criteria decision-making based on factors such as failure impact, maintenance cost, and system importance. Natural Gradient Boosting (NGB) is employed to forecast asset degradation and estimate failure probability and Remaining Useful Life (RUL) with high accuracy. These predictive insights formed the basis for prioritizing assets for replacement or disposal. A Parallel Genetic Algorithm (PGA) is developed to optimize disposal schedules and support long-term planning within operational and financial constraints. This approach balances budget limitations with criticality and RUL outputs to generate efficient replacement strategies. Integrating AHP, NGB, and PGA within a unified decision-support system highlights the potential of hybrid analytical models in modernizing public infrastructure management. The results show that the hybrid approach performs significantly better than traditional approaches in terms of System Average Interruption Frequency Index (SAIFI) and System Average Interruption Duration Index (SAIDI). This approach supports proactive maintenance, reduces systemic risks, and enhances the overall resilience and performance of power distribution networks.

Keywords

power grids asset prioritization disposal planning natural gradient boosting (NGB)parallel genetic algorithm (PGA)

Get full access to this article

View all access options for this article.

References

Kouloumpis

Konstantzos

Chroni

, et al. Does the circularity end justify the means? A life cycle assessment of preparing waste electrical and electronic equipment for reuse. Sustain Prod Consum 2023; 41: 291–304. DOI: 10.1016/j.spc.2023.08.008.

ZurHeiden

Priefer

Beverungen

. Predictive maintenance on the energy distribution grid–design and evaluation of a digital industrial platform in the context of a smart service system. IEEE Trans Eng Manag 2024; 71: 3641–3655. DOI: 10.1109/TEM.2024.3352819.

Almasoudi

. Enhancing power grid resilience through real-time fault detection and remediation using advanced hybrid machine learning models. Sustainability 2023; 15(10): 8348. DOI: 10.3390/su15108348.

Alhanaf

Balik

Farsadi

. Intelligent fault detection and classification schemes for smart grids based on deep neural networks. Energies 2023; 16(22): 7680. DOI: 10.3390/en16227680.

Alhanaf

Farsadi

Balik

. Fault detection and classification in a ring power system with DG penetration using hybrid CNN-LSTM. IEEE Access 2024; 12: 59953–59975. DOI: 10.1109/ACCESS.2024.3394166.

Anwar

Yousaf

, et al. Robust fault detection and classification in power transmission lines via ensemble machine learning models. Sci Rep 2025; 15(1): 2549. DOI: 10.1038/s41598-025-86554-2.

Wang

Xie

Wang

. Application of artificial intelligence in power system monitoring and fault diagnosis. Energies 2023; 16(14): 5477. DOI: 10.3390/en16145477.

Tian

Wang

Guo

, et al. A hybrid deep learning and ensemble learning mechanism for damaged power line detection in smart grids. Soft Comput 2022; 26(20): 10553–10561. DOI: 10.1007/s00500-021-06482-x.

Aljafari

Satpathy

Thanikanti

, et al. Supervised classification and fault detection in grid-connected PV systems using 1D-CNN: simulation and real-time validation. Energy Rep 2024; 12: 2156–2178. DOI: 10.1016/j.egyr.2024.08.008.

10.

Hoang

Ozkan

Badr

, et al. Integrating degradation forecasting into distribution grids’ advanced distribution management systems. Int J Electr Power Energy Syst 2023; 150: 109071. DOI: 10.1016/j.ijepes.2023.109071.

11.

Zhang

Yan

Zhang

, et al. Distributed architecture of power grid asset management and future research directions. IEEE Access 2022; 10: 57588–57595. DOI: 10.1109/ACCESS.2022.3179119.

12.

Muñoz-Villamizar

Rafavy

Casey

. Machine learning and optimization-based modeling for asset management: a case study. Int J Prod Perform Manag 2022; 71(4): 1149–1163. DOI: 10.1108/IJPPM-05-2020-0206.

13.

Kala

Kre

Gnassou

, et al. Assets management on electrical grid using Faster-RCNN. Ann Oper Res 2022; 308(1): 307–320. DOI: 10.1007/s10479-020-03650-4.

14.

Rosati

Romeo

Cecchini

, et al. From knowledge-based to big data analytic model: a novel IoT and machine learning based decision support system for predictive maintenance in Industry 4.0. J Intell Manuf 2023; 34(1): 107–121. DOI: 10.1007/s10845-022-01960-x.

15.

Rajora

Sanz-Bobi

Domingo

, et al. An open-source toolbox for asset management based on the asset condition for the power system. IEEE Access 2025. DOI: 10.1109/ACCESS.2025.3551663.

16.

Manninen

Ramlal

Singh

, et al. Multi-stage deep learning networks for automated assessment of electricity transmission infrastructure using fly-by images. Elec Power Syst Res 2022; 209: 107948. DOI: 10.1016/j.epsr.2022.107948.

17.

Petrozziello

Troiano

Serra

, et al. Deep learning for volatility forecasting in asset management. Soft Comput 2022; 26(17): 8553–8574. DOI: 10.1007/s00500-022-07161-1.

18.

Jin

Kim

Chan

, et al. Deep machine learning-based asset management approach for oil-immersed power transformers using dissolved gas analysis. IEEE Access 2024; 12: 27794–27809. DOI: 10.1109/ACCESS.2024.3366905.

19.

Zhukabayeva

Pervez

Mardenov

, et al. A traffic analysis and node categorization-aware machine learning-integrated framework for cybersecurity intrusion detection and prevention of WSNs in smart grids. IEEE Access 2024; 12: 91715–91733. DOI: 10.1109/ACCESS.2024.3422077.

20.

Mour

Smith

. Machine learning based on reinforcement learning for smart grids: predictive analytics in renewable energy management. Sustain Cities Soc 2024; 109: 105510. DOI: 10.1016/j.scs.2024.105510.

21.

Murshed

Chamana

Schmitt

, et al. Sizing PV and BESS for grid-connected microgrid resilience: a data-driven hybrid optimization approach. Energies 2023; 16(21): 7300. DOI: 10.3390/en16217300.

22.

Gjorgiev

Sansavini

. Identifying and assessing power system vulnerabilities to transmission asset outages via cascading failure analysis. Reliab Eng Syst Saf 2022; 217: 108085. DOI: 10.1016/j.ress.2021.108085.

23.

Zhou

. A prioritization method for switchgear maintenance based on equipment failure mode analysis and integrated risk assessment. IEEE Trans Power Deliv 2023; 39(2): 728–739. DOI: 10.1109/TPWRD.2023.3335351.

24.

Zhou

. A multi-evidence fusion-based integrated method for health assessment of medium voltage switchgears in power grid. IEEE Trans Power Deliv 2022; 38(2): 1406–1415. DOI: 10.1109/TPWRD.2022.3215242.

25.

Popović

ŽN

Krsman

Rakić

, et al. A risk-based multi-criteria maintenance planning of distribution feeders. Int J Electr Power Energy Syst 2025; 165: 110379. DOI: 10.1016/j.ijepes.2024.110379.

26.

The. https://www.kaggle.com/datasets/zoya77/power-grid-asset-prioritization-rul-dataset

27.

Keynia

Mirhosseini

Heydari

, et al. A budget allocation and programming-based RCM approach to improve the reliability of power distribution networks. Energy Rep 2022; 8: 5591–5602. DOI: 10.1016/j.egyr.2022.04.029.

Data-driven approaches for asset prioritization and disposal planning in public power grids

Abstract

Keywords

Get full access to this article

References