This paper proposes an intelligent framework for analyzing and forecasting operating parameters of urban electric networks in Tashkent. Monthly data (84 observations, 2018-2024) on electricity purchase, technological losses, planned and actual indicators were preprocessed using interpolation for missing values, outlier smoothing based on the interquartile range, and min-max normalization to the range [0, 1]. To reveal heterogeneous operating regimes, clustering based on self-organizing maps (SOM) was applied, while Principal Component Analysis (PCA) was used for factor analysis and visualization. For forecasting excess electrical energy losses, three approaches were compared: autoregressive parametric stochastic systems (ARPSS), a multilayer perceptron neural network (ANN/MLP), and a combined model integrating several expert MLP networks. The comparative evaluation shows that the ARPSS model produces high prediction errors, whereas intelligent models significantly improve accuracy. The average relative error equals 42.8% for ARPSS, 6.1% for ANN, and 3.7% for the combined model. The proposed approach can support operational decision-making in urban distribution networks by improving the reliability of loss forecasting.
Keywords
Electric Power IndustryArtificial Neural NetworksSelf-Organizing MapsClusteringPrincipal Component AnalysisForecasting
References
Z. Nazari and P. Musilek, “Impact of digital transformation on the energy sector: A review,” Algorithms, vol. 16, no. 4, art. 211, 2023, [Online]. Available: https://doi.org/10.3390/a16040211.
P. Maroufkhani, K. C. Desouza, R. K. Perrons, and M. Iranmanesh, “Digital transformation in the resource and energy sectors: A systematic review,” Resources Policy, vol. 76, art. 102622, Jun. 2022, [Online]. Available: https://doi.org/10.1016/j.resourpol.2022.102622.
T. Hong and S. Fan, “Probabilistic electric load forecasting: A tutorial review,” International Journal of Forecasting, vol. 32, no. 3, pp. 914-938, 2016, [Online]. Available: https://doi.org/10.1016/j.ijforecast.2015.11.011.
H. K. Alfares and M. Nazeeruddin, “Electric load forecasting: Literature survey and classification of methods,” International Journal of Systems Science, vol. 33, no. 1, pp. 23-34, 2002, [Online]. Available: https://doi.org/10.1080/00207720110067421.
H. S. Hippert, C. E. Pedreira, and R. C. Souza, “Neural networks for short-term load forecasting: A review and evaluation,” IEEE Transactions on Power Systems, vol. 16, no. 1, pp. 44-55, Feb. 2001, [Online]. Available: https://doi.org/10.1109/59.910780.
E. A. Feinberg and D. Genethliou, “Load forecasting,” in Applied Mathematics for Restructured Electric Power Systems: Optimization, Control, and Computational Intelligence. Boston, MA, USA: Springer, 2005, pp. 269-285, [Online]. Available: https://doi.org/10.1007/0-387-23471-3_12.
I. Blinov, V. Radziukynas, P. Shymaniuk, A. Dyczko, K. Stecuła, V. Sychova, V. Miroshnyk, and R. Dychkovskyi, “Smart management of energy losses in distribution networks using deep neural networks,” Energies, vol. 18, no. 12, art. 3156, 2025, [Online]. Available: https://doi.org/10.3390/en18123156.
M. Khudayarov and B. Bobonazarov, “Assessment of technical losses of electrical energy in distribution networks based on artificial neural networks,” AIP Conference Proceedings, vol. 2686, art. 020001, 2022, [Online]. Available: https://doi.org/10.1063/5.0112968.
M. Yakubov, M. Talipov, and U. Nurullaev, “An optimized Lagrangian approach to reactive power compensation in nonlinear traction power-supply systems,” Vibroengineering Procedia, vol. 60, pp. 724-730, Dec. 2025, [Online]. Available: https://doi.org/10.21595/vp.2025.25604.
Y. Zhang, T. Huang, and E. F. Bompard, “Big data analytics in smart grids: a review,” Energy Informatics, vol. 1, art. 8, 2018, [Online]. Available: https://doi.org/10.1186/s42162-018-0007-5.
S. A. Nabavi, S. Mohammadi, N. H. Motlagh, S. Tarkoma, and P. Geyer, “Deep learning modeling in electricity load forecasting: Improved accuracy by combining DWT and LSTM,” Energy Reports, vol. 12, pp. 2873-2900, 2024, [Online]. Available: https://doi.org/10.1016/j.egyr.2024.08.070.
R. J. Hyndman and A. B. Koehler, “Another look at measures of forecast accuracy,” International Journal of Forecasting, vol. 22, no. 4, pp. 679-688, 2006, [Online]. Available: https://doi.org/10.1016/j.ijforecast.2006.03.001.
N. A. Manov et al., New Information Technologies in Operational Management of Electric Power Systems. Yekaterinburg, Russia: Ural Branch RAS Publ., 2002.
V. G. Kurbatsky and N. V. Tomin, “Short-term forecasting of electrical load using new information technologies,” Bulletin of Amur State University, no. 27, pp. 48-51, 2004.
T. A. Dubrova, Statistical Methods of Forecasting. Moscow, Russia: YUNITI-DANA, 2003.
V. B. Shumansky, V. G. Kurbatsky, and N. V. Tomin, “Forecasting outdoor air temperature based on an artificial neural network model,” in Proc. Interregional Scientific and Technical Conf., Bratsk, Russia, 2005, pp. 4-14.
V. G. Kurbatsky and N. V. Tomin, “Methods of artificial intelligence in electric power systems,” in Proc. 3rd Int. Workshop on Liberalization and Modernization of Power Systems, 2006, p. 223.
I. T. Jolliffe, Principal Component Analysis, 2nd ed. New York, NY, USA: Springer, 2002, [Online]. Available: https://doi.org/10.1007/b98835.
V. G. Kurbatsky and N. V. Tomin, “Management in the electric power industry using artificial intelligence methods,” Electrics, no. 9, pp. 20-28, 2005.
A. V. Panteleev and T. A. Letova, Optimization Methods in Examples and Problems. Moscow, Russia: Vysshaya Shkola, 2008.
A. V. Panteleev and I. F. Dmitrakov, “Comparative analysis of the effectiveness of the simulated annealing method for searching for the global extremum of multivariable functions,” Scientific Bulletin MGTU GA. Applied Mathematics and Informatics, no. 145, pp. 26-31, 2009.
A. V. Artemyev, Yu. S. Zhelezko, and O. V. Savchenko, Calculation, Analysis and Rationing of Electric Power Losses in Electric Networks. Moscow, Russia: NC ENAS, 2003.
V. G. Kurbatsky and N. V. Tomin, “Forecasting of electrical load using artificial neural networks,” Electrics, no. 7, pp. 26-32, 2006.
V. N. Shchelkalin, “Hybrid models and methods of forecasting time series based on the ‘Caterpillar’-SSA and Box-Jenkins methods,” East European Journal of Advanced Technologies, vol. 5, no. 4, pp. 43-62, 2014, [Online]. Available: https://doi.org/10.15587/1729-4061.2014.28172.
V. V. Strizhov and E. A. Krymova, Methods of Selecting Regression Models. Moscow, Russia: Dorodnitsyn Computing Center, 2010.
V. P. Borovikov and G. I. Ivchenko, Forecasting in the STATISTICA System in the Windows Environment, 2nd ed. Moscow, Russia: Finance and Statistics, 2006.
M. Talipov, O. Ilyasov, O. Kovaleva, B. Begmatov, and Z. Ismailova, “Environmental protection of railway wastewater using natural diatomite sorbents: development and validation of a three-layer filtration strip,” Vibroengineering Procedia, vol. 60, pp. 473-478, Dec. 2025, [Online]. Available: https://doi.org/10.21595/vp.2025.25627.
O. Ilyasov, M. Talipov, I. Khurramov, and M. Tirkasheva, “Technical and ecological evaluation of a diatomite-based filter strip for cleaning polluted runoff from a railway embankment,” Vibroengineering Procedia, vol. 60, pp. 515-521, Dec. 2025, [Online]. Available: https://doi.org/10.21595/vp.2025.25269.
M. M. Talipov, O. T. Aliev, O. R. Ilyasov, and O. V. Kovaleva, “Modern method for purifying wastewater from railway embarking using diatomite in a filter band,” Proc. Int. Conf. on Thermal Engineering (ICTEA 2024), vol. 1, no. 1, 2024.
S. Sulaymanov, M. M. Talipov, R. S. Razikov, O. R. Ilyasov, and O. V. Kovaleva, “Protection of the environment from pollution by wastewater from railway transport using natural sorbents,” Proc. Int. Conf. on Thermal Engineering (ICTEA 2024), vol. 1, no. 1, 2024.
M. M. Talipov, “Computational modeling and analysis of mechanical power consumption in train assemblers’ work,” Proc. Int. Conf. on Applied Innovation in IT, vol. 13, no. 2, pp. 419-426, 2025, [Online]. Available: https://doi.org/10.25673/120513.
O. T. Aliev, M. M. Talipov, Kh. M. Kamilov, and O. R. Ilyasov, “Hygienic examination of employees of locomotive crews of UTY JSC companies,” AIP Conference Proceedings, vol. 2624, no. 1, art. 040057, 2023, [Online]. Available: https://doi.org/10.1063/5.0134056.
E. Shipacheva, S. Shaumarov, A. Gulamov, and M. M. Talipov, “Modeling of interaction of external enclosing structures of buildings with the internal and external environments,” ICTEA: Int. Conf. on Thermal Engineering, vol. 1, no. 1, 2024.
E. Shipacheva, S. Shaumarov, A. Gulamov, M. M. Talipov, and S. Kandakharov, “Water structure and its influence on cement stone and concrete properties,” ICTEA: Int. Conf. on Thermal Engineering, vol. 1, no. 1, 2024.
J. Vesanto and E. Alhoniemi, “Clustering of the self-organizing map,” IEEE Transactions on Neural Networks, vol. 11, no. 3, pp. 586-600, May 2000, [Online]. Available: https://doi.org/10.1109/72.846731.
