Calculation of the steady-state mode of the electric network using a genetic algorithm
https://doi.org/10.37493/2307-907X.2025.1.2
Abstract
Introduction. This article discusses the application of evolutionary optimization methods in problems of calculating the steady-state mode of an electrical network, in particular, genetic algorithms.
Goal. Description of the population optimization method, which can be used to calculate the steady state of the electric network.
Materials and methods. The object of the study is the population optimization algorithm. The subject of the study is the objective function of the genetic algorithm, which can be used to find voltage levels in the nodes of the electric network. The methods used in the work include an optimization method based on genetic algorithms, as well as the classical Newton method for calculating the steady-state mode of an electrical network.
Results and discussion. The paper presents the main elements of a genetic algorithm for calculating the steady-state mode of an electrical network, defines an optimized target function, and presents the calculation results in comparison with Newton method.
Conclusion. Based on the results of the conducted study, it can be concluded that the calculation of the steady state can be considered from the point of view of the optimization problem of power imbalances, the use of a genetic algorithm for calculating the electrical network mode is possible, but the accuracy of the results strongly depends on the number of iterations, although it does not require large computing power and complex calculations.
Supporting agencies: The research was carried out within the framework of the state assignment "Laboratory of Artificial Intelligence of Electric Power Systems" (subject code: FENG-2024-0007)
About the Authors
V. I. Polischuk
Yugra State University
Russian Federation
Russian Federation
Vladimir I. Polischuk, Dr. Sci. (Techn.), Professor, Professor of the School
Polytechnic School
628012; 16, Chekhov str.; Khanty-Mansiysk
Scopus ID: 16478590800
V. A. Tkachenko
Yugra State University
Russian Federation
Russian Federation
Vsevolod A. Tkachenko, Cand. Sci. (Tech.), Associate Professor
Polytechnic School
628012; 16, Chekhov str.; Khanty-Mansiysk
Scopus ID: 57210291005, Researcher ID: W-3652-2019
A. O. Shepelev
Yugra State University
Russian Federation
Russian Federation
Aleksandr O. Shepelev, Cand. Sci. (Techn.), Associate Professor
Polytechnic School
628012; 16, Chekhov str.; Khanty-Mansiysk
Scopus ID: 57195281176, Researcher ID: A-6600-2017
References
1. Manusov VZ, Levin VM, Khalyasmaa AI, Akhyoev JS. Application of artificial intelligence methods in the problems of technical diagnostics of electrical equipment of electrical systems : monograph. Ed. VZ. Manusov. Novosibirsk: NSTU Publishing House; 2020. 446 p. (In Russ.).
2. Solodyankin MS, Kolontsov VD, Tkachenko VA. Analysis of the application of artificial neural networks for assessing the technical condition of 6-10 kV power transformers. Yugra State University Bulletin. 2024;20(4):51-54. doi: 10.18822/byusu20240451-54. (In Russ.).
3. Lobanov VA, Valiullin KR. Study of the possibility of using an artificial neural network for the problem of classifying the operating mode of an electrical network. In University complex as a regional center of education, science and culture. Proceedings of the All-Russian scientific and methodological conference (with international participation), Orenburg, January 23-25, 2020. Orenburg: Orenburg State University; 2020. P. 2751-2758. (In Russ.).
4. Kaukin AS, Pavlov PN, Kosarev VS. Short-term forecasting of electricity prices using generative neural networks. Business informatics. 2023;17(3):7-23. doi: 10.17323/2587-814X.2023.3.7.23. (In Russ.).
5. Vyalkova SA, Nadtoka II, Kornyukova OA. Application of neural networks for forecasting the electricity consumption of a megalopolis. Russian Internet Journal of Industrial Engineering. 2023;10(4):12-16. doi: 10.24892/RIJIE/20230403. (In Russ.).
6. Tkachenko VA. Development of methods and algorithms for optimizing the circuit and mode parameters of electrical systems, including minigrid : dissertation for the degree of candidate of technical sciences. Khanty-Mansiysk; 2023. 223 p. (In Russ.).
7. Magdy Mohamed El-Saadawi. A genetic-based approach for solving optimal power flow problem (Dept. E). Mansoura Engineering Journal. 2020;29(2):12-26.
8. César Augusto Hernández Suárez. Optimal power flow through artificial intelligence techniques. Tecnura. 2021;25(69):150-170.
9. Solopov RV, Samulchenkov AS, Ziryukin VI. Genetic algorithm as a tool for modeling calculations of electric power systems. Journal of Applied Informatics. 2021;16(6(96)):43-53 doi: 10.37791/2687-0649-2021-16-6-43-53.
10. Utyuzh TI. Application of a genetic optimization algorithm for reactive power compensation. Molodoj uchenyj = Young scientist. 2021;20(362):104-106. (In Russ.).
11. Ayuyev BI, Davydov VV, Erokhin PM, Neuimin VG. Computational models of power flow distribution in electrical systems: monograph. Ed. PI. Bartolomey. Moscow: Flinta: Science; 2008. 256 p.: ill. (In Russ.).
12. Simon D. Evolutionary Optimization Algorithms. Trans. from English by AV Logunov. Moscow: DMK Press; 2020. 1002 p. (In Russ.).
13. Idelchik VI. Electrical Systems and Networks: Textbook for Universities. Moscow: Energoatomizdat; 1989. 592 p. (In Russ.).
14. GitHub. Available from: https://github.com/Sevaat/Newtons_Method [Accessed 28 January 2025].
15. GitHub. Available from: https://github.com/Sevaat/Genetic_Algorithm [Accessed 28 January 2025].
Review
For citations:
Polischuk V.I., Tkachenko V.A., Shepelev A.O. Calculation of the steady-state mode of the electric network using a genetic algorithm. Newsletter of North-Caucasus Federal University. 2025;(1):21-28. (In Russ.) https://doi.org/10.37493/2307-907X.2025.1.2
Views:
102
Email this article 