ANALYSIS OF ELECTRICITY QUALITY IN 0.4 KV NETWORKS USING MACHINE LEARNING ALGORITHMS

This article discusses the application of machine learning algorithms for analyzing and determining the quality of electric power in 0.4 kV electrical networks. The experimental results were obtained using a power quality meter (PKE-A-S4) at a 160 kVA transformer substation; the data were recorded in the device’s memory and copied to a computer in xlsx format. Statistical data on electric power quality obtained using machine learning algorithms allowed us to determine the dependence of the voltage and phase current non-sinusoidality coefficient, frequency deviation, and voltage deviation over a period of 24 hours. Based on the statistical results and analysis of machine learning algorithms, the electric power quality indicators of a 0.4 kV rural network were compared with the standards of GOST 32144-2013. A statistical analysis of electric power quality indicators in a low-voltage network and its visualization were performed using the capabilities of the Python programming language and machine learning algorithms. The dependence of the electric power quality indicators is considered and close dependencies are analyzed.

electricity quality, voltage deviation, frequency deviation, non-sinusoidal coefficient, voltage fluctuations, machine learning, correlation.

1. Zhezhelenko I.V., Saenko Yu.L. Electricity quality indicators and their control at industrial enterprises. – 3rd ed., revised and supplemented – M.: Energoatomizdat. – 2000. – 252.

2. Nemtsev G.A. Quality management of electricity in power supply systems / G.A. Nemtsev. Cheboksary: Chuvash Publishing House. Unita. – 2013. – 372 p.

3. Rakhimov O. S., Mirzoev D. N., Gracheva E. I. Experimental study of indicators of quality and loss of electricity in low-voltage rural electric networks //News of higher educational institutions. Energy problems. – 2021. – Vol. 23. – No. 3. – pp. 209-222.

4. Rakhimov, O. S. Modeling of low-voltage rural electric networks 10/0.4 kV / O. S. Rakhimov, D. N. Mirzoev // Bulletin of the PITTU named after academician M.S. Osimi. – 2018. – № 4(9). – Pp. 37-42. – EDN FHEINT.

5. A. K. Thakur, S. Singh and S. P. Singh, “Machine Learning based Detection and Classification of Power Quality Disturbances in Smart Grid System,” 2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT), New Delhi, India, 2022, pp. 1-6, doi: 10.1109/GlobConPT57482.2022.9938352

6. K. Rawal and A. Ahmad, “A Comparative Analysis of Supervised Machine Learnin Algorithms for Electricity Demand Forecasting,” 2022 Second International Conference on Power, Control and Computing Technologies (ICPC2T), Raipur, India. – 2022, pp. 1-6, doi: 10.1109/ICPC2T53885.2022.9776960.

7. Terezija Matijašević, Tomislav Antić, Tomislav Capuder «A systematic reviewof-machine learning applications in the operation of smart distribution systems» Energy Reports 8.     – 2022, pp. 12379–12407 https://doi.org/10.1016/j.egyr.2022.09.068

2026-03-27