Keywords
mathematical modeling
production
artificial intelligence
energy management
How to Cite
Abstract
The article focuses on exploring the processes of mathematical modeling of energy efficiency in manufacturing enterprises, taking into account physical principles and modern artificial intelligence approaches. The study aims to analyze the potential of mathematical modeling to improve energy efficiency in enterprises through the use of artificial intelligence technologies in a dynamic production environment. The findings demonstrate that mathematical modeling is a vital tool in enterprise energy management, especially in the context of expanding production capacity and limited resources. The emphasis is placed on a comprehensive approach to energy consumption management, which considers both internal technical characteristics of the enterprise and the influence of external factors. It has been shown that integrating artificial intelligence into mathematical models significantly enhances prediction accuracy, enables adaptive resource management, and ensures rapid response to changes in production conditions. The study reveals that effective energy management relies on continuous data collection, processing, and analysis of energy consumption. It has been established that the use of mathematical models complemented by intelligent algorithms makes it possible to consider a wide range of parameters, including technological, meteorological, economic, and seasonal indicators. This creates a solid foundation for optimizing energy flows and stabilizing enterprise operations under fluctuating production loads. Despite the high level of automation, the human factor remains essential. The reliable operation of intelligent energy efficiency management systems is only possible with continuous oversight by qualified personnel capable of assessing the adequacy of proposed solutions and adjusting them according to target indicators. The practical significance of this study lies in establishing an effective foundation for implementing energy-efficient solutions in enterprises by integrating mathematical modeling, artificial intelligence, and expert supervision.
References
1. Deshko, V. I., Bilous, I. Yu., & Hurska, Yu. V. (2016). Do zastosuvannia rehresiinoho analizu dlia prohnozuvannia enerhospozhyvannia budivel [On the application of regression analysis for forecasting energy consumption in buildings]. In Enerhetychnyi menedzhment: stan ta perspektyvy rozvytku – PEMS’16 (p. 77). NTUU “KPI”. http://pems.kpi.ua/public/conferences/51/PEMS-2016/Zbirnyk_tez_2016.pdf (in Ukrainian)
2. Matsui, A. M., & Kondratets, V. O. (2018). Matematychne modeliuvannia avtomatychnoho kontroliu enerhoefektyvnosti podribnennia rudy kulovymy mynamy pry spratsiuvanni futerovky [Mathematical modeling of automatic control of ore grinding energy efficiency in ball mills as the lining wears]. Problemy informatsiinykh tekhnolohii – Problems of Information Technologies, (1), 111–117. http://nbuv.gov.ua/UJRN/Pit_2018_1_17 (in Ukrainian)
3. Nakhodov, V. F., Ivanko, D. O., & Holovko, A. V. (2013). Vybir metodiv matematychnoho modeliuvannia protsesiv enerhospozhyvannia v systemakh operatyvnoho kontroliu enerhoefektyvnosti [Selection of mathematical modeling methods for energy consumption processes in energy efficiency monitoring systems]. Enerhetyka: ekonomika, tekhnolohii, ekolohiia, (Special issue), 20–27. https://ela.kpi.ua/server/api/core/bitstreams/75c3a87c-175d-4b54-a328-b9926f0d5d2a/content (in Ukrainian)
4. Ponomar, O. A. (2022). Matematychne modeliuvannia enerhoefektyvnosti v lokalnykh enerhetychnykh ostrovakh hibrydnoho typu [Mathematical modeling of energy efficiency in local hybrid-type energy islands] (Bachelor’s thesis, Kyiv National University of Technologies and Design). KNUTD. https://er.knutd.edu.ua/handle/123456789/22803 (in Ukrainian)
5. Nakhodov, V. F., Borychenko, O. V., & Ivanko, D. O. (2013). Kontrol efektyvnosti enerhovykorystannia v systemi enerhetychnoho menedzhmentu [Control of energy use efficiency in the energy management system]. Visnyk Kyivskoho natsionalnoho universytetu tekhnolohii ta dyzainu – Bulletin of Kyiv National University of Technologies and Design, (6), 67–77. http://nbuv.gov.ua/UJRN/Vknutd_2013_6_10 (in Ukrainian)
6. Sanytskyi, M. A., Kotiv, M. V., & Marushchak, U. D. (2014). Matematychne modeliuvannia v doslidzhenni enerhoefektyvnosti budivelnykh obiektiv [Mathematical modeling in the study of energy efficiency of construction sites]. Enerhoefektyvnist v budivnytstvi ta arkhitekturi, (6), 254–259. https://repositary.knuba.edu.ua/items/cea5a18b-fd53-4bb3-870a-a6bf23b4f168 (in Ukrainian)
7. Sukhodolia, O. M. (2022). Shtuchnyi intelekt v enerhetytsi: Analitychna dopovid [Artificial intelligence in energy: Analytical report]. NISS. https://doi.org/10.53679/NISS-analytrep.2022.09 (in Ukrainian)
8. Digitap. (2024). Energy management: An effective way to ensure efficient energy consumption. digitap.com.ua. https://digitap.com.ua/decisions/upravlinnya-energoresursamy
9. Boodhoo, K. (2024). Machine learning methodologies for real-world resilient energy systems (EngD thesis). University of Nottingham. https://eprints.nottingham.ac.uk/79870
10. Kyriakarakos, G. (2025). Artificial intelligence and the energy transition. Sustainability, 17(3), 1140. https://doi.org/10.3390/su17031140
11. Hafemeister, D. (2008). Physics of energy efficient buildings. https://home.agh.edu.pl/~kozlow/fizyka/energooszczedny%20dom/Physics%20of%20Energy%20Efficient%20Buildings.pdf
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Roman Vytvytskyi, Olha Morushko, Viktor Mosiurchak, Iryna Skobel, Roman Morushko