Vol. 337 No. 1 (2026)
DOI https://doi.org/10.18799/24131830/2026/1/5149
Forecasting energy efficiency in the fuel and energy complex based on the MLP model
Relevance. In the modern global economy, the demand for energy resources is steadily increasing, driven by the need to ensure energy security, support sustainable societal development, and simultaneously reduce the negative technogenic impact on the environment. At the state policy level, the main priorities are defined as the digitalization of industry – primarily the energy sector – the implementation of resource-efficient technologies, and the optimization of energy consumption. Under these conditions, accurate and reliable forecasting of energy efficiency becomes a key instrument for ensuring economic growth, increasing investment attractiveness, and supporting science-based strategic decision-making. Aim. To develop a methodology for forecasting energy efficiency based on the energy intensity indicator. The proposed methodology includes preliminary statistical processing of the source data using the log-normal distribution, validation of adequacy through the Kolmogorov–Smirnov criterion, and correlation analysis. At the next stage, hyperparameters are optimized, after which a Multilayer Perceptron (MLP) artificial neural network model is adapted and applied for evaluating and verifying the reliability of forecasts. The effectiveness of the methodology is demonstrated using information collected from 23 enterprises of the fuel and energy complex. Methods. Data processing was carried out using the log-normal distribution, while predictive validity was evaluated with the Kolmogorov–Smirnov test and correlation analysis. The number of neurons in the input, hidden, and output layers, as well as key hyperparameters (batch size, learning rate, activation function, solver, and number of epochs), were optimally selected based on the minimization of the MAPE error. To verify model stability, testing was performed on training and test datasets in a 20/5 proportion. Results. The developed MLP model demonstrated high forecasting accuracy: the error amounted to 4.35% on the training dataset and 1.21% on the test dataset. The model predicted a steady decrease in energy intensity up to 2030, when this indicator is expected to reach approximately 0.913 kg of oil equivalent per USD. These results confirm the potential for significant improvement in energy efficiency, cost reduction, resource savings, and enhancement of environmental sustainability. Conclusion. The method and model proposed in this study provide a reliable scientific basis for high-precision forecasting, strategic decision-making, and the implementation of innovative developments in the fuel and energy complex.
Keywords:
energy efficiency, energy intensity, forecasting, neural network, MLP (Multilayer Perceptron), hyperparameter selection, energy saving, MAPE error, activation function, epochs, energy security
References:
1. Zharov V., Tokarenko A. Quantitative assessment of sustainability level of industrial enterprises. BIO Web of Conferences Aquaculture, 2023, vol. 05003. Available at: https://doi.org/10.1051/bioconf/20248405003 (accessed 15 September 2023).
2. Rakhmonov I.U., Ushakov V.Ya., Niyozov N.N., Kurbanov N.N. Forecasting electricity consumption using the principal component analysis method. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2024, vol. 334, no. 2, pp. 198–209. (In Russ.) DOI: 10.18799/24131830/2024/12/4731
3. Zakharchenko N., Kosaretskyi Y., Andreichenko A. Methodical provision of assessment of the efficiency of the functioning of a high-tech industrial enterprise on the basis of score-coefficient method. Economic Innovations, 2023, vol. 25, no. 87, pp. 18–26. Available at: https://doi.org/10.31520/ei.2023.25.2 (accessed 15 September 2023).
4. Bişkin O.T., Çifci A. Forecasting of Turkey's electrical energy consumption using LSTM and GRU Networks. Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi, 2021, vol. 8, pp. 656–667. DOI: 10.35193/bseufbd.935824 (accessed 15 September 2023).
5. Dinolov O. Energy efficiency of induction motor drives: state of the art, analysis and recommendations. Energies, 2023, vol. 16, no. 7136. Available at: https://doi.org/10.3390/en162071-36 (accessed 15 September 2023).
6. Rakhmonov I.U., Ushakov V.Ya., Niyozov N.N., Kurbonov N.N. Forecasting electricity consumption by LSTM neural network. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2023, vol. 334, no. 2, pp. 125–133. (In Russ.) Available at: https://doi.org/10.18799/24131830/2023/12/4407 (accessed 15 September 2023).
7. Li G., Zhang H., Bo R. A novel method to reduce power loss using distributed reactive power control. International Journal of Electrical Power & Energy Systems, 2014, vol. 61, pp. 188–193. DOI: https://doi.org/10.1016/j.ijepes.2014.03.021
8. Rakhmonov I.U., Ushakov V.Ya., Niyozov N.N., Kurbonov N.N. Forecasting electricity consumption using principal component analysis. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2024, vol. 335, no. 12, pp. 198–209. (In Russ.) DOI: 10.18799/24131830/2024/12/4731
9. Alam M.M., Nishi T., Liu Z., Fujiwara T. A Novel sampling-based optimal motion planning algorithm for energy-efficient robotic pick and place. Energies, 2023, vol. 16, no. 6910, pp. 1–22. Available at: https://doi.org/10.3390/en16196910 (accessed 15 September 2023).
10. Shinkevich A.I. Modeling the efficiency of using digital technologies of energy and resource saving technologies at petrochemical enterprises. International Journal of Energy Economics and Policy, 2020, vol. 10 (5), pp. 1–6. Available at: https://doi.org/10.32479/ijeep.9837 (accessed 15 September 2023).
11. Ugolnikov A.V., Makarov N.V. Application of automation systems for monitoring and energy efficiency accounting indicators of mining enterprises compressor facility operation. Journal of Mining Institute, 2019, vol. 236, pp. 245–248. DOI: 10.31897/PMI.2019.2.245
12. Yuce B., Mourshed M., Rezgui Y. A smart forecasting approach to district energy management. Energies, 2017, vol. 10, no. 1073. DOI: https://doi.org/10.3390/en10081073
13. Maryasin O.Y. Two-stage problem of optimizing smart grid energy consumption at the enterprise. 4th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency, 2022, pp. 808–813. DOI: 10.1109/SUMMA57301.2022.9973902.
14. Dzhedzhula V., Yepifanova I. Optimization of energy saving potential of industrial enterprises. 11th International Conference on Advanced Computer Information Technologies (ACIT), 2021, pp. 433–436. DOI: 10.1109/ACIT52158.2021.9548428.
15. Chang S.C. Effects of financial developments and income on energy consumption. International Review of Economics and Finance, 2015, vol. 35, pp. 28–40. Available at: http://dx.doi.org/10.1016/j.iref.2014.08.011 (accessed 15 September 2023).
16. Val P.V., Popov Yu.P. Concept for developing a system for forecasting power consumption of an industrial enterprise in the conditions of the wholesale market. Industrial Energy, 2011, no. 10, pp. 31–35. (In Russ.)
17. Kirschbaum C., Verstege J.A. Reactive power control for loss minimization in smart grids with high penetration of renewable energy sources. Innovative Smart Grid Technologies (ISGT), IEEE PES, 2012, pp. 1–8. DOI: https://doi.org/10.1109/ISGT.2012.6175715
18. Liao H., Chuang C.S., Lu L. Hybrid ant colony optimization with particle swarm optimization for power losses minimization considering voltage stability in power system. Journal of Electrical Engineering & Technology, 2012, vol. 7 (2), pp. 246–254. DOI: https://doi.org/10.5370/JEET.2012.7.2.246
19. Fan C., Zhang L., Kurbonov N.N., Rakhmonov I.U., Wang G. Research on the ablation resistance of tic particle-reinforced aluminium-based composite coatings on armature surface. Coatings, 2024, vol. 14, no. 549. DOI: https://doi.org/10.3390/coatings14050549
20. Taylor J.W., McSharry P.E. Short-term load forecasting methods: an evaluation based on European data. IEEE Transactions on Power Systems, 2007, vol. 22, no. 4, pp. 2213–2219. DOI: https://doi.org/10.1109/TPWRS.2007.907583
21. Kesornsit W., Sirisathitkul Y. Hybrid machine learning model for electricity consumption prediction using random forest and artificial neural networks. Applied Computational Intelligence and Soft Computing, 2022, no. 1562942. DOI: ttps://doi.org/10.1155/2022/1562942
22. Motulsky H.J., Head T., Clarke P.B.S. Analyzing lognormal data: a nonmathematical practical guide. Pharmacology Research & Perspectives, 2025, vol. 13, no. 2, Article ID: 100049. Available at: https://doi.org/10.1016/j.pharmr.2025.100049 (accessed 15 September 2023).
23. Mirjalili S. Evolutionary multi-layer perceptron. Evolutionary Algorithms and Neural Networks: Theory and Applications, 2019, vol. 780, pp. 87–104. (Studies in Computational Intelligence). Available at: https://doi.org/10.1007/978-3-319-93025-1_7 (accessed 15 September 2023).
24. Naderi E., Abdollahzadeh H., Narimani H. A new modified teaching-learning algorithm for optimal reactive power dispatch problem with discrete control variables. Engineering Applications of Artificial Intelligence, 2013, vol. 26 (10), pp. 2282–2292. DOI: https://doi.org/10.1016/j.engappai.2013.05.012 (accessed 15 September 2023).
25. Wang J. Trap distribution and along-surface discharge characterization of aromatic compound-modified silicone gel. IEEE Transactions on Dielectrics and Electrical Insulation, 2024. DOI: 10.1109/TDEI.2024.3456096
26. Rakhmonov I.U., Niyozov N.N., Nimatov K.B., Ushakov V.Ya., Omonov F.B., Reymov K.M., Najimova A.M. Mathematical model for reducing active power losses by regulating reactive power at enterprises with continuous production mode. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2025, vol. 336, no. 2, pp. 159–171. DOI: 10.18799/24131830/2025/2/4730
