Abstract

Electrical energy losses in distribution networks represent a significant challenge in modern power systems, affecting overall efficiency and sustainability. Accurate prediction of these losses is crucial for optimizing network performance, reducing operational costs, and enhancing energy management strategies. This study explores the application of deep neural networks (DNNs) for forecasting electrical energy losses in distribution systems. A dataset comprising real-world network parameters, load profiles, and environmental conditions was utilized to train and validate the model. The proposed DNN-based approach demonstrates high predictive accuracy compared to traditional statistical and machine learning methods. The results indicate that deep learning techniques can effectively model complex nonlinear dependencies in electrical networks, enabling more precise loss estimation. The findings contribute to the development of intelligent energy management solutions, ultimately supporting the transition toward more resilient and efficient power distribution systems.

Keywords: electrical energy losses, distribution networks, deep neural networks, loss prediction, energy efficiency

References

1. Blinov, I., Kyrylenko, O., Parus, E., & Rybina, O. (2022). Decentralized market coupling with taking account power systems transmission network constraints. Power Systems Research and Operation. Studies in Systems, Decision and Control, 388, 1-21. https://doi.org/10.1007/978-3-030-82926-1_1
2. On the electricity market: Law of Ukraine № 2019-VIII of 13.04.2017.
3. Resolution 14.03.2018 No. 307 On approval of the Market Rules.
4. NEURC Resolution "On Approval of Distribution Network Code" No. 310 of 14.03.2018.
5. Blinov, I. V., Trach, I. V., Parus, Y. V., Derevianko, D. G., & Khomenko, V. M. (2022). Voltage and reactive power regulation in distribution networks by the means of distributed renewable energy sources. Tekhn. elektr., 2, 60–69. https://doi.org/10.15407/techned2022.02.060
6. ENTSO-E. (2024). ENTSO-E RDI roadmap 2024 – 2034: Innovation missions to build the power system for a carbon-neutral Europe. 38 p.
7. El Hajji, H., Mahmoudi, H., & Labbadi, M. (2020). The electromagnetic interference caused by high voltage power lines along the electrical railway equipment. International Journal of Electrical and Computer Engineering, 10(5), 4581–4891. https://doi.org/10.11591/ijece.v10i5
8. Mohsen, S., Bajaj, M., Kotb, H., Pushkarna, M., Alphonse, S., & Ghoneim, S. S. (2023). Efficient artificial neural network for smart grid stability prediction. International Transactions on Electrical Energy Systems, 1(9974409), 1-13. https://doi.org/10.1155/2023/9974409
9. Mohammad, F., & Kim, Y. C. (2020). Energy load forecasting model based on deep neural networks for smart grids. International Journal of System Assurance Engineering and Management, 11, 824–834. https://doi.org/10.1007/s13198-019-00884-9
10. Dusza, D., & Kosobudzki, G. (2018). Reactive power measurements based on its geometrical interpretation. 14th Selected Issues of Electrical Engineering and Electronics (WZEE). https://doi.org/10.1109/WZEE.2018.8749118
11. Polyanska, A., Pazynich, Y., Mykhailyshyn, K., Babets, D., & Tos, P. (2024). Aspects of energy efficiency management for rational energy resource utilization. Rudarsko-Geolosko-Naftni Zbornik, 39(3), 13–26. https://doi.org/10.17794/rgn.2024.3.2
12. Muralitharan, K., Sakthivel, R., & Vishnuvarthan, R. (2018). Neural network-based optimization approach for energy demand prediction in smart grid. Neurocomputing, 273, 199-208. https://doi.org/10.1016/j.neucom.2017.08.017
13. Souhe, F. G. Y., Mbey, C. F., Boum, A. T., & Ele, P. (2021). Forecasting of electrical energy consumption of households in a smart grid. International Journal of Energy Economics and Policy, 11(6), 221-233. https://doi.org/10.32479/ijeep.11761
14. Pivnyak, G., Aziukovskyi, O., Papaika, Y., Cabana, E. C., Miedziński, B., Polnik, B., Jamróż, A., & Polyanska, A. (2024). Managing the power supply energy efficiency by means of higher harmonics. Polityka Energetyczna, 27(4), 59–80. https://doi.org/10.33223/epj/191813
15. Ford, V., Siraj, A., & Eberle, W. (2014). Smart grid energy fraud detection using artificial neural networks. In 2014 IEEE symposium on computational intelligence applications in smart grid (CIASG), Orlando, FL, USA, 09-12 December 2014 (pp. 1-6). https://doi.org/10.1109/CIASG.2014.7011557
16. Hou, G., et al. (2016). A novel algorithm for multi-node load forecasting based on big data of distribution network. International Conference on Advanced Electronic Science and Technology (AEST 2016), November, 655-667.
17. Dychkovskyi, R., Saik, P., Sala, D., & Cabana, E. C. (2024). The current state of the non-ore mineral deposits mining in the concept of the Ukraine reconstruction in the post-war period. Mineral Economics. https://doi.org/10.1007/s13563-024-00436-z
18. Hatziargyriou, N., Wang, X., & Tsoukalas, L. H. (2020). A new methodology for nodal load forecasting in deregulated power systems. IEEE Power Engineering Review, 48–51. http://hdl.handle.net/123456789/14566
19. Gooi, H. B., Han, X. S., Han, L., & Pan, Z. Y. (2012). Ultra-short-term multi-node load forecasting – a composite approach. IET Generation, Transmission & Distribution, 6, 436–444. https://doi.org/10.1049/iet-gtd.2011.0524
20. Shcherba, A. A., Suprunovska, N. I., & Shcherba, M. A. (2018). Transient analysis in circuits of electric discharge installations with voltage feedback taking into account the recovery time of locking properties of their semiconductor switches. Tekhn. elektr., (3), 43–47. https://doi.org/10.15407/techned2018.03.043
21. Bezerra, U. H., & Falcao, D. M. (1986). Short-term forecasting of nodal active and reactive load in electric power system. Second International Conference on Power System Monitoring and Control, 266, 18-22.
22. Miroshnyk, V., Chernenko, P., & Shymaniuk, P. (2020). Univariable short-term forecast of nodal electrical loads of energy systems. Tekhn. elektr., 2, 67-73. https://doi.org/10.15407/techned2020.02.067
23. Benchmark systems for network integration of renewable and distributed energy resources. (2014). ELECTRA. http://e-cigre.org/publication/ELT_273_8-benchmark-systems-for-network-integration-of-renewable-and-distributedenergy-resources
24. Kyrylenko, O., Stogniy, B., Denysiuk, S., & Sopel, M. (2024). Smart-monitoring of electric power systems. Tekhnichna Elektrodynamika, (5), 048. https://doi.org/10.15407/techned2024.05.048
25. Styczynski, Z. A., Rudion, K., Orths, O., & Strunz, K. (2006). Design of benchmark of medium voltage distribution network for investigation of DG integration. IEEE Power Engineering Society General Meeting, Montreal, Canada, 18-22 June. https://doi.org/10.1109/PES.2006.1709447
26. Lepolesa, L. J., Achari, S., & Cheng, L. (2022). Electricity theft detection in smart grids based on deep neural network. IEEE Access, 10, 39638-39655. https://doi.org/10.1109/CIASG.2014.7011557
27. Shymaniuk, P., Miroshnyk, V., & Blinov, I. (2022). Estimation of electrical losses in the distribution network based on nodal electrical load forecasts. 2022 IEEE 3rd KhPI Week on Advanced Technology (KhPIWeek), Kharkiv, Ukraine, 03-07 October, 1-4. https://doi.org/10.1109/KhPIWeek57572.2022.9916407
28. Sander, J., Ester, M., Kriegel, H. P., & Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96), Portland,
29. Pivnyak, G., Zhezhelenko, I., & Papaika, Yu. (2013). Normalization of voltage quality as the way to ensure energy saving in power supply systems. Energy Efficiency Improvement of Geotechnical Systems - Proceedings of the International Forum on Energy Efficiency, 11–18. https://doi.org/10.1201/b16355-3
30. Papaika, Yu. A., Lysenko, O. H., Koshelenko, Ye. V., & Olishevskyi, I. H. (2021). Mathematical modeling of power supply reliability at low voltage quality. Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, (2), 97–103. https://doi.org/10.33271/nvngu/2021-2/097
31. Kosobudzki, G., Rogoza, M., Lysenko, O., & Papaika, Y. (2018). Frequency and parametric characteristics of direct current pulse conversion filter of a contactless locomotive. 14th Selected Issues of Electrical Engineering and Electronics (WZEE). https://doi.org/10.1109/WZEE.2018.8748987
32. Pivnyak, G., Azukovskiy, O., Papaika, Yu., Cabana, E. C., Olczak, P., & Dyczko, A. (2021). Assessment of power supply energy efficiency by voltage quality criterion. Rynek Energii, 4(155), 75–84. ISSN 1425-5960
33. Kolb, A., Pazynich, Y., Mirek, A., & Petinova, O. (2020). Influence of voltage reserve on the parameters of parallel power active compensators in mining. E3S Web of Conferences, 201, 01024. https://doi.org/10.1051/e3sconf/202020101024
34. IEEE 1547. (2003). Standard for interconnecting distributed resources with electric power systems.
35. International Electrotechnical Commission. (2002). Electromagnetic compatibility (EMC) -- Part 2-4: Environment-compatibility levels in industrial plants for low-frequency conducted disturbances (Standard IEC 61000-2-4).