Composite Index for Managing Emergency Repair in Electrical Utilities under Heterogeneous Incident Data
DOI:
https://doi.org/10.25729/esr.2026.01.0003Keywords:
Emergency repair, human-machine system, composite index, fuzzy logic, multi-agent system, heterogeneous data, decision support systemAbstract
The paper focuses on the management of emergency repair crews in distribution systems characterized by high emergency rates and heterogeneous incident data. The study examines the human-machine system, Human–Tools–Logistics, which necessitates a compact, interpretable, and data-resilient readiness indicator. The scientific novelty lies in the development of a non-compensatory composite operational readiness index for crews, based on the geometric aggregation of three sub-indices: Human, Tools, and Logistics.
A two-stage methodology for constructing the composite operational readiness index is proposed. In the first stage, heterogeneous data and expert knowledge regarding personnel, equipment, logistics, and environmental conditions are integrated through a multi-agent data fusion framework. In the second stage, normalized sub-indices (H/T/L) are developed using fuzzy logic. Finally, the operational readiness index is aggregated as a normalized weighted geometric mean, ensuring its non-compensatory nature.
* Corresponding author.
E-mail: starkcom8@mail.ru
DOI: 10.25729/esr.2026.01.0003
Received December 7, 2025. Revised January 26, 2025. Accepted January 30, 2026. Available online March 31, 2026.
This is an open-access article under a Creative Commons Attribution-NonCommercial 4.0 International License.
© 2026 ESI SB RAS and authors. All rights reserved.
Simulation software was developed to model emergency scenarios in Moscow power grids. For a fixed point in time, the index values are calculated for multiple crews to match them with an incident and establish the most effective crew for that incident. The impact of temperature, traffic congestion, crew size, along with personnel experience and qualifications is analyzed. The analysis demonstrates diminishing returns on crew size and saturation of the experience curve, alongside the significant influence of adverse meteorological conditions and traffic congestion.
The proposed index is compared with existing simulation-based, probabilistic, and optimization-oriented models, as well as fuzzy-logic and decision support systems. The findings demonstrate that the proposed operational readiness index offers superior interpretability for dispatcher decision-making and can be seamlessly integrated into assignment and routing optimization tasks, facilitating bottleneck identification and dispatcher training.
The paper focuses on the management of emergency repair crews in distribution systems characterized by high emergency rates and heterogeneous incident data. The study examines the human-machine system, Human–Tools–Logistics, which necessitates a compact, interpretable, and data-resilient readiness indicator. The scientific novelty lies in the development of a non-compensatory composite operational readiness index for crews, based on the geometric aggregation of three sub-indices: Human, Tools, and Logistics.
A two-stage methodology for constructing the composite operational readiness index is proposed. In the first stage, heterogeneous data and expert knowledge regarding personnel, equipment, logistics, and environmental conditions are integrated through a multi-agent data fusion framework. In the second stage, normalized sub-indices (H/T/L) are developed using fuzzy logic. Finally, the operational readiness index is aggregated as a normalized weighted geometric mean, ensuring its non-compensatory nature.
* Corresponding author.
E-mail: starkcom8@mail.ru
DOI: 10.25729/esr.2026.01.0003
Received December 7, 2025. Revised January 26, 2025. Accepted January 30, 2026. Available online March 31, 2026.
This is an open-access article under a Creative Commons Attribution-NonCommercial 4.0 International License.
© 2026 ESI SB RAS and authors. All rights reserved.
Simulation software was developed to model emergency scenarios in Moscow power grids. For a fixed point in time, the index values are calculated for multiple crews to match them with an incident and establish the most effective crew for that incident. The impact of temperature, traffic congestion, crew size, along with personnel experience and qualifications is analyzed. The analysis demonstrates diminishing returns on crew size and saturation of the experience curve, alongside the significant influence of adverse meteorological conditions and traffic congestion.
The proposed index is compared with existing simulation-based, probabilistic, and optimization-oriented models, as well as fuzzy-logic and decision support systems. The findings demonstrate that the proposed operational readiness index offers superior interpretability for dispatcher decision-making and can be seamlessly integrated into assignment and routing optimization tasks, facilitating bottleneck identification and dispatcher training.
References
“High wear and tear and increased incident rates: electrical networks in Krasnoyarsk need to be replaced,” Rosseti Siberia Official Website, Nov. 2, 2025. [Online]. Available: https://www.rosseti-sib.ru/news/vysokiy_iznos_i_rost_avariynosti_elektricheskie_seti_v_krasnoyarske_trebuyut_zameny/. Accessed on: Nov. 2, 2025. (In Russian)
A. S. Kinzhalieva, A. A. Khanova, “A simulation model for managing field service teams of a power grid company,” Sci. Bull. Novosib. State Tech. Univ., no. 2/3, pp. 77–94, 2020. DOI: 10.17212/1814-1196-2020-2-3-77-94. (In Russian)
T. Ding, Z. Wang, W. Jia, B. Chen, C. Chen, M. Shahidehpour, “Multiperiod distribution system restoration with routing repair crews, mobile electric vehicles, and soft-open-point networked microgrids,” IEEE Trans. Smart Grid, vol. 11, no. 6, pp. 4795–4808, 2020. DOI: 10.1109/TSG.2020.3001952.
Q. Shi, H. Wan, W. Liu, H. Han, Z. Wang, F. Li, “Preventive allocation and post-disaster cooperative dispatch of emergency mobile resources for improved distribution system resilience,” International Journal of Electrical Power & Energy Systems, vol. 152, Art. no. 109238, 2023. DOI: 10.1016/j.ijepes.2023.109238.
S. Lei, C. Chen, Y. Li, Y. Hou, “Resilient disaster recovery logistics of distribution systems: co-optimize service restoration with repair crew and mobile power source dispatch,” IEEE Trans. Smart Grid, vol. 10, no. 6, pp. 6187–6202, 2019. DOI: 10.1109/TSG.2019.2899353.
H. D. Kaushik, R. A. Jacob, S. Chowdhury, J. Zhang, “Distribution network restoration: resource scheduling considering coupled transportation-power networks,” arXiv: arXiv:2404.13422, 2024. DOI: 10.48550/arXiv.2404.13422.
H. Shuai, F. Li, B. She, X. Wang, J. Zhao, “Post-storm repair crew dispatch for distribution grid restoration using stochastic Monte Carlo tree search and deep neural networks,” International Journal of Electrical Power & Energy Systems, vol. 144, Art. no. 108477, 2023. DOI: 10.1016/j.ijepes.2022.108477.
S. S. Mikhailova, et al., “Calculation of field crew readiness indicators based on a model of complex accidents at critical infrastructure facilities,” Nelineinyi Mir, vol. 23, no. 3, pp. 15–24, 2025. DOI: 10.18127/j20700970-202503-03. (In Russian)
M. A. Nosov, L. A. Sabinina, N. V. Anisova, “Optimization of the quantitative composition of repair teams in the management of the quality of industrial entity equipment maintenance,” News of the Tula state university. Technical sciences, vol. 11, no. 2, pp. 202–210, 2025. (In Russian)
L. Bukowski, S. Werbińska-Wojciechowska, “Using fuzzy logic to support maintenance decisions according to Resilience-Based Maintenance concept,” Eksploat. Niezawodn. – Maint. Reliab., vol. 23, no. 2, pp. 294–307, 2021. DOI: 10.17531/ein.2021.2.9.
O. Blyskun, V. Herasymenko, Y. Kolomiiets, Y. Honcharenko, Y. Yaroshenko, “Algorithm of determining the readiness level of the flight crew based on fuzzy logic approaches,” Sci. Eur., no. 80-2, p. 46–49, 2021. DOI: 10.24412/3162-2364-2021-80-2-46-49.
J. E. Naranjo, C. A. Mora, D. F. Bustamante Villagómez, M. G. Mancheno Falconi, M. V. Garcia, “Wearable sensors in industrial ergonomics: enhancing safety and productivity in industry 4.0,” Sensors, vol. 25, no. 5, Art. no. 1526, 2025. DOI: 10.3390/s25051526.
D. S. Soloviev, “The objectification method of the weight coefficients for decision-making in multicriteria problems,” Scientific and Technical Journal of Information Technologies, Mechanics and Optics, vol. 23, no. 1. pp. 161–168, 2023. DOI: 10.17586/2226-1494-2023-23-1-161-168. (In Russian)
B. Ghasemkhani, et al, “Machine learning model development to predict power outage duration (POD): A case study for electric utilities,” Sensors, vol. 24, no. 13, Art. no. 4313, 2024. DOI: 10.3390/s24134313.
F. Amani, F. Ardali, A. Kargarian, “Learning optimal crew dispatch for grid restoration following an earthquake,” arXiv: arXiv:2509.04308, 2025. DOI: 10.48550/arXiv.2509.04308.
V. G. Deı̆neko, G. J. Woeginger, “On the dimension of simple monotonic games,” European Journal of Operational Research, vol. 170, no. 1, pp. 315–318, 2006. DOI: 10.1016/j.ejor.2004.09.038.
A. Yu. Onufrey, A. A. Razumov, V. V. Kakaev, “A method of optimizing the structure of hierarchical distributed control systems,” Scientific and Technical Journal of Information Technologies, Mechanics and Optics, vol. 23, no. 1, pp. 44–53, 2023. DOI: 10.17586/2226-1494-2023-23-1-44-53. (In Russian)
S. Greco, A. Ishizaka, M. Tasiou, G. Torrisi, “On the methodological framework of composite indices: A review of the issues of weighting, aggregation, and robustness,” Social Indicators Research, vol. 141, no. 1, pp. 61–94, 2019. DOI: 10.1007/s11205-017-1832-9.
R. Chen, Y. Ji, G. Jiang, H. Xiao, R. Xie, P. Zhu, “Composite index construction with expert opinion,” Journal of Business and Economic Statistics, vol. 41, no. 1, pp. 67–79, 2023. DOI: 10.1080/07350015.2021.2000418.
D. I. Muromtsev, et al, “Building knowledge graphs of regulatory documentation based on semantic modeling and automatic term extraction,” Scientific and Technical Journal of Information Technologies, Mechanics and Optics, vol. 21, no. 2. pp. 256–266, 2021. DOI: 10.17586/2226-1494-2021-21-2-256-266. (In Russian)
“Data on current registered notifications for emergency repair of engineering communications, structures and roads,” 2026. [Online]. Available: https://data.mos.ru/opendata/62461. Accessed: Jan. 24, 2026.
Open-meteo. Python. [Online]. Available: https://github.com/open-meteo/python-requests. Accessed: Jan. 24, 2026.
Faker 40.11.1 documentation, 2026. [Online]. Available: https://faker.readthedocs.io/en/master/index.html. Accessed: Jan. 24, 2026.
L. E. Yelle, “The learning curve: Historical review and comprehensive survey,” Decis. Sci., vol. 10, no. 2, pp. 302–328, 1979. DOI: 10.1111/j.1540-5915.1979.tb00026.x.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Energy Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
