Centralized System for Automatically Restoring Normal Operation of a Power District with Distributed Energy Resources
DOI:
https://doi.org/10.24160/0013-5380-2026-9-4-16Keywords:
power district, distributed energy resources, restoration of normal operation, centralized automatic control system, graph neural networks, reinforcement learningAbstract
The article deals with the development of principles for organizing centralized control for automatically restoring and optimizing the normal operation of power districts with distributed energy resources (DER). The aim of the study is to achieve more reliable operation of distribution power grids through making a shift to intelligent control without human intervention. The research methods are based on artificial intelligence technologies that combine the mathematical apparatus of graph neural networks and deep reinforcement learning algorithms. The article proposes a method for post-emergency restoration of the normal operation of a power district with DER, which allows overcoming the computational limitations of conventional combinatorial approaches. The proposed automatic control was tested using the example of a power district with a medium-voltage distribution network using the pandapower software environment. It is shown that the combined use of graph neural networks and reinforcement learning ensures high speed and efficiency of control action synthesis. The advantages of and potential for implementing the proposed intelligent automatic control to ensure fault tolerance in power districts with DER are substantiated.
References
1. Воропай Н.И. Направления и проблемы трансформации электроэнергетических cистем. – Электричество, 2020, № 7, с. 12–21.
2. Илюшин П.В. Системный подход к развитию и внедрению распределенной энергетики и возобновляемых источников энергии в России. – Энергетик, 2022, № 4, с. 20–27.
3. Kulikov A.L. et al. Control of Electric Power Quality Indicators in Distribution Networks Comprising a High Share of Solar Photovoltaic and Wind Power Stations. – Energy Reports, 2022, vol. 8, No. S9, pp. 1501–1514, DOI: 10.1016/j.egyr.2022.08.217.
4. Илюшин П.В. О влиянии распределенной генерации на работу устройств автоматического включения резервного питания. – Релейная защита и автоматизация, 2017, № 4 (29), с. 28–36.
5. Пат. RU № 2728523 C1. Способ восстановления сети электроснабжения / Й. Бромбах, И. Маккензен, К. Бускер, 2020.
6. Марченко А.И., Фишов А.Г., Мурашкина И.С. Противоаварийная автоматика для создания и управления режимами локальных интеллектуальных энергосистем на базе малой генерации. – Альтернативная энергетика и экология, 2024, № 1 (418), с. 225–234.
7. Фишов А.Г. и др. Активные распределительные электрические сети с децентрализованным мультиагентным управлением режимом. Ч. 2. – Электричество, 2022, № 11, с. 29–45.
8. Пат. RU № 2784610 C1. Способ децентрализованной синхронизации и восстановления нормального режима аварийно разделенной электрической сети с генераторами / А.Г. Фишов, А.А. Осинцев, 2022.
9. Армеев Д.В., Фишов А.Г. Мультиагентное децентрализованное регулирование частоты и управление балансом активной мощности в электрических сетях с распределенной генерацией. – Релейная защита и автоматизация, 2024, № 4 (57), с. 24–33.
10. Tomin N. et al. Management of Voltage Flexibility from Inverter-Based Distributed Generation Using Multi-Agent Reinforcement Learning. – Energies, 2021, vol. 14, DOI: 10.3390/en14248270.
11. Пат. RU № 160078 U1. Устройство автоматического восстановления нормального режима системы электроснабжения / Е.А. Третьяков, 2016.
12. Glavic M. (Deep) Reinforcement Learning for Electric Power System Control and Related Problems: A Short Review and Perspectives. – Annual Reviews in Control, 2019, vol. 48, pp. 22–35. DOI: 10.1016/j.arcontrol.2019.09.008.
13. Jacob R.A. et al. Real-Time Outage Management in Active Distribution Networks Using Reinforcement Learning Over Graphs. – Nature Communications, 2024, vol. 15, DOI: 10.1038/s41467-024-49207-y.
14. Zhong J. et al. Service Restoration for Distribution System via Monte-Carlo Tree Search and Learned Model. – 17th Int. Conf. on Probabilistic Methods Applied to Power Systems, 2022, DOI: 10.1109/PMAPS53380.2022.9810609.
15. Майоров А. Развитие системы оперативно-технологического управления электросетевым комплексом в рамках концепции цифровой трансформации 2030. – Электроэнергия. Передача и распределение, 2019, № S2 (13), с. 2–7.
16. Marot A. et al. Learning to Run a Power Network with Trust. – Electric Power Systems Research, 2022, vol. 212, DOI: 10.1016/j.epsr.2022.108487.
17. Макаров А.Ю. Цифровизация электрических сетей. Практический опыт. М.: Экономика, 2019, 128 с.
18. Куликов А.Л., Гурина Л.А., Томин Н.В. Метод восстановления режимов энергорайонов с распределенными энергетическими ресурсами на основе графовых нейронных сетей. – Известия РАН. Энергетика, 2026, № 1, с. 44–68.
19. Scarselli F. et al. The Graph Neural Network Model. – IEEE Transactions on Neural Networks, 2009, vol. 20, No. 1, pp. 61–80, DOI: 10.1109/TNN.2008.2005605.
20. Solheim Ø.R., Høverstad B.A., Korpås M. Using Graph Neural Networks in Reinforcement Learning with Application to Monte Carlo Simulations in Power System Reliability Analysis. – IEEE Access, 2024, vol. 12, pp. 160175–160189, DOI: 10.1109/ACCESS.2024.3486354.
21. Van Nooten C.C. et al. Graph Neural Networks for Assessing the Reliability of the Medium-Voltage Grid. – Applied Energy, 2025, vol. 384, DOI: 10.1016/j.apenergy.2025.125401.
22. Zhang Y., Karve P.M., Mahadevan S. Graph Neural Networks for Power Grid Operational Risk Assessment Under Evolving Grid Topology. – Applied Energy, 2025, vol. 380, DOI: 10.1016/j.apenergy.2024.124793.
23. Mnih V. et al. Human-Level Control Through Deep Reinforcement Learning. – Nature, 2015, vol. 518, pp. 529–533, DOI: 10.1038/nature14236.
24. Sidorov D. et al. A Dynamic Analysis of Energy Storage with Renewable and Diesel Generation Using Volterra Equations. – IEEE Transactions on Industrial Informatics, 2020, vol. 16, No. 5, pp. 3451–3459, DOI: 10.1109/TII.2019.2932453.
25. Thurner L. et al. Pandapower – An Open-Source Python Tool for Convenient Modeling, Analysis, and Optimization of Electric Power Systems. – IEEE Transactions on Power Systems, Nov. 2018, vol. 33, No. 6, pp. 6510–6521, DOI: 10.1109/TPWRS.2018.2829021.
26. Simon D. Evolutionary Optimization Algorithms: Biologically-Inspired and Population-Based Approaches to Computer Intelligence. Hoboken, New Jersey: John Wiley & Sons Inc., 2013, 742 p.
27. Press W.H. et al. Numerical Recipes: The Art of Scientific Computing. New York: Cambridge University Press, 2007, 1262 p.
28. IEEE Std. 1547-2018. Standard for Interconnection and Interoperability of Distributed Energy Resources with Associated Electric Power Systems Interfaces. 2018, 138 p.
---
Работа выполнена в рамках проекта государственного задания (№ FWEU-2026-0012) программы фундаментальных исследований РФ на 2026–2030 гг.
#
1. Voropay N.I. Elektrichestvo – in Russ. (Electricity), 2020, No. 7, pp. 12–21.
2. Ilyushin P.V. Energetik – in Russ. (Power Engineer), 2022, No. 4, pp. 20–27.
3. Kulikov A.L. et al. Control of Electric Power Quality Indicators in Distribution Networks Comprising a High Share of Solar Photovoltaic and Wind Power Stations. – Energy Reports, 2022, vol. 8, No. S9, pp. 1501–1514, DOI: 10.1016/j.egyr.2022.08.217.
4. Ilyushin P.V. Releynaya zashchita i avtomatizatsiya – in Russ. (Relay Protection and Automation), 2017, No. 4 (29), pp. 28–36.
5. Pat. RU No. 2728523 C1. Sposob vosstanovleniya seti elektro-snabzheniya (A Way to Restore the Power Supply Network) / Y. Brombah, I. Makkenzen, K. Busker, 2020.
6. Marchenko A.I., Fishov A.G., Murashkina I.S. Al’ternativ-naya energetika i ekologiya – in Russ. (Alternative Energy and Ecology), 2024, No. 1 (418), pp. 225–234.
7. Fishov A.G. et al. Elektrichestvo – in Russ. (Electricity), 2022, No. 11, pp. 29–45.
8. Pat. RU No. 2784610 C1. Sposob detsentralizovannoy sinhronizatsii i vosstanovleniya normal’nogo rezhima avariyno razdelennoy elektricheskoy seti s generatorami (A Method of Decentralized Synchronization and Restoration of the Normal Operation of an Emergency Divided Electrical Network with Generators) / A.G. Fishov, A.A. Osintsev, 2022.
9. Armeev D.V., Fishov A.G. Releynaya zashchita i avtomatiza-tsiya – in Russ. (Relay Protection and Automation), 2024, No. 4 (57), pp. 24–33.
10. Tomin N. et al. Management of Voltage Flexibility from Inverter-Based Distributed Generation Using Multi-Agent Reinforcement Learning. – Energies, 2021, vol. 14, DOI: 10.3390/en14248270.
11. Pat. RU No. 160078 U1. Ustroystvo avtomaticheskogo vosstanovleniya normal’nogo rezhima sistemy elektrosnabzheniya (Device for Automatic Restoration of the Normal Mode of the Power Supply System) / E.A. Tret’yakov, 2016.
12. Glavic M. (Deep) Reinforcement Learning for Electric Power System Control and Related Problems: A Short Review and Perspectives. – Annual Reviews in Control, 2019, vol. 48, pp. 22–35. DOI: 10.1016/j.arcontrol.2019.09.008.
13. Jacob R.A. et al. Real-Time Outage Management in Active Distribution Networks Using Reinforcement Learning Over Graphs. – Nature Communications, 2024, vol. 15, DOI: 10.1038/s41467-024-49207-y.
14. Zhong J. et al. Service Restoration for Distribution System via Monte-Carlo Tree Search and Learned Model. – 17th Int. Conf. on Probabilistic Methods Applied to Power Systems, 2022, DOI: 10.1109/PMAPS53380.2022.9810609.
15. Mayorov A. Elektroenergiya. Peredacha i raspredelenie – in Russ. (Electricity. Transmission and Distribution), 2019, No. S2 (13), pp. 2–7.
16. Marot A. et al. Learning to Run a Power Network with Trust. – Electric Power Systems Research, 2022, vol. 212, DOI: 10.1016/j.epsr.2022.108487.
17. Makarov A.Yu. Tsifrovizatsiya elektricheskih setey. Prakticheskiy opyt (Digitalization of Electrical Networks. Practical Experience). M.: Ekonomika, 2019, 128 p.
18. Kulikov A.L., Gurina L.A., Tomin N.V. Izvestiya RAN. Energetika – in Russ. (News of the Russian Academy of Sciences. Energy Industry), 2026, No. 1, pp. 44–68.
19. Scarselli F. et al. The Graph Neural Network Model. – IEEE Transactions on Neural Networks, 2009, vol. 20, No. 1, pp. 61–80, DOI: 10.1109/TNN.2008.2005605.
20. Solheim Ø.R., Høverstad B.A., Korpås M. Using Graph Neural Networks in Reinforcement Learning with Application to Monte Carlo Simulations in Power System Reliability Analysis. – IEEE Access, 2024, vol. 12, pp. 160175–160189, DOI: 10.1109/ACCESS.2024.3486354.
21. Van Nooten C.C. et al. Graph Neural Networks for Assessing the Reliability of the Medium-Voltage Grid. – Applied Energy, 2025, vol. 384, DOI: 10.1016/j.apenergy.2025.125401.
22. Zhang Y., Karve P.M., Mahadevan S. Graph Neural Networks for Power Grid Operational Risk Assessment Under Evolving Grid Topology. – Applied Energy, 2025, vol. 380, DOI: 10.1016/j.apenergy.2024.124793.
23. Mnih V. et al. Human-Level Control Through Deep Reinforcement Learning. – Nature, 2015, vol. 518, pp. 529–533, DOI: 10.1038/nature14236.
24. Sidorov D. et al. A Dynamic Analysis of Energy Storage with Renewable and Diesel Generation Using Volterra Equations. – IEEE Transactions on Industrial Informatics, 2020, vol. 16, No. 5, pp. 3451–3459, DOI: 10.1109/TII.2019.2932453.
25. Thurner L. et al. Pandapower – An Open-Source Python Tool for Convenient Modeling, Analysis, and Optimization of Electric Power Systems. – IEEE Transactions on Power Systems, Nov. 2018, vol. 33, No. 6, pp. 6510–6521, DOI: 10.1109/TPWRS.2018.2829021.
26. Simon D. Evolutionary Optimization Algorithms: Biologically-Inspired and Population-Based Approaches to Computer Intelligence. Hoboken, New Jersey: John Wiley & Sons Inc., 2013, 742 p.
27. Press W.H. et al. Numerical Recipes: The Art of Scientific Computing. New York: Cambridge University Press, 2007, 1262 p.
28. IEEE Std. 1547-2018. Standard for Interconnection and Interoperability of Distributed Energy Resources with Associated Electric Power Systems Interfaces. 2018, 138 p
---
The work was carried out within the framework of the state assignment project (no. FWEU-2026-0012) of the fundamental research program of the Russian Federation for 2026–2030.
