Skip to content
POWER ENGINEERING: economics, technique, ecology
ISSN 1813-5420 · e‑ISSN 2308-7382 Open Access · CC BY 4.0
Vol. · Issue 3 · 2026 Oct 12, 2026 MONITORING, DIAGNOSTICS AND MANAGEMENT BY ENERGY PROCESSES AND EQUIPMENT

DIGITAL TWIN STRUCTURE FOR SHORT-TERM ELECTRICAL LOAD FORECASTING AT A DAIRY PLANT

AH
Andrii Hoienko Corresponding National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute», Ukraine
AC
Anatolii Cherniavskyi National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute», Ukraine
Pages119-129 PublishedOct 12, 2026 LicenseOpen Access
PDF (Ukrainian)
VOL · ISS 3 · 2026 85 View issue

Abstract

The study aims to develop a digital twin structure and a method for forming input data for short-term electrical load forecasting at a dairy plant, taking into account its current and expected technological states. The plant boundary is defined by the main electricity metering point, and the target variable is the mean active power over a 15-minute interval. Historical load, equipment and process states, product and buffer parameters, refrigeration conditions, the production plan, and calendar and weather variables are synchronized according to the time at which they become available. The digital twin converts measurements and planning records into a formalized technological context for the forecasting model. A functional structure linking primary data sources, the digital twin core, the forecasting module, decision support, and subsequent state updating is proposed. The composition of the current state, the expected state at the forecast horizon, and the complete model input vector is formalized. A rule is established according to which each forecasting sample contains only measurements, plans, and external forecasts available when the load forecast is issued. An illustrative one-hour-ahead example separates binary operation indicators, quantitative process variables, and refrigeration variables before combining them in the model input vector. The example demonstrates input formation only; a numerical load forecast requires a model trained on operating-plant data. The proposed structure provides a methodological basis for day-ahead and intraday load-profile forecasting, early detection of possible power-limit violations, coordination of flexible operations, and planning under restricted grid supply or on-site generation. Forecast accuracy and the practical effect of state-aware forecasting must be evaluated on a chronologically separated dataset from an operating dairy plant.

Keywords

#dairy plant #digital twin #electrical load #energy management #energy monitoring #food industry #short-term forecasting #technological state

References

  1. D. Mariano-Hernández, L. Hernández-Callejo, F. S. García, O. Duque-Perez, and A. L. Zorita-Lamadrid, "A review of energy consumption forecasting in smart buildings: Methods, input variables, forecasting horizon and metrics," Applied Sciences, vol. 10, no. 23, Art. no. 8323, 2020, doi: 10.3390/app10238323.
  2. Verkhovna Rada of Ukraine, Law of Ukraine No. 2019-VIII, "On the Electricity Market," Apr. 13, 2017, as amended. [Online]. Available: https://zakon.rada.gov.ua/laws/show/2019-19
  3. M. Al Shimmari and D. Wallom, "Short-term load forecasting using UK non-domestic businesses to enable demand response aggregators' participation in electricity markets," in 2023 IEEE PES Grid Edge Technologies Conference & Exposition, San Diego, CA, USA, 2023, doi: 10.1109/GridEdge54130.2023.10102712.
  4. Cabinet of Ministers of Ukraine, Resolution No. 600, "On Approval of the Procedure for Determining and Applying Maximum Electricity Consumption Capacity," May 24, 2024, as amended. [Online]. Available: https://zakon.rada.gov.ua/laws/show/600-2024-%D0%BF
  5. A. Santecchia, I. Kantor, R. Castro-Amoedo, and F. Maréchal, "Industrial Flexibility as Demand Side Response for Electrical Grid Stability," Frontiers in Energy Research, vol. 10, Art. no. 831462, 2022, doi: 10.3389/fenrg.2022.831462.
  6. M. R. Wodicker, J. Nelson, and N. G. Johnson, "Unified dispatch of grid-connected and islanded microgrids," Frontiers in Energy Research, vol. 11, Art. no. 1257050, 2024, doi: 10.3389/fenrg.2023.1257050.
  7. P. Wohlgenannt, L. Moosbrugger, V. Vetter, S. Hegenbart, M. Kolhe, E. Eder, and P. Kepplinger, "Energy cost and emission optimization in food industry using deep reinforcement learning and Transformer-based load forecasting," Energy Conversion and Management: X, vol. 28, Art. no. 101364, 2025, doi: 10.1016/j.ecmx.2025.101364.
  8. J. B. Heluany and V. Gkioulos, "A review on digital twins for power generation and distribution," International Journal of Information Security, vol. 23, pp. 1171-1195, 2024, doi: 10.1007/s10207-023-00784-x.
  9. X. Feng and J. Wan, "Digital Twins for Discrete Manufacturing Lines: A Review," Big Data and Cognitive Computing, vol. 8, no. 5, Art. no. 45, 2024, doi: 10.3390/bdcc8050045.
  10. C. Krupitzer, T. Noack, and C. Borsum, "Digital Food Twins Combining Data Science and Food Science: System Model, Applications, and Challenges," Processes, vol. 10, no. 9, Art. no. 1781, 2022, doi: 10.3390/pr10091781.
  11. T. Y. Melesse, M. S. Peer, S. Ramasamy, V. Sivasubramaniyam, M. Braggio, and P. F. Orrù, "Digital Twin for Energy-Intelligent Bakery Operations: Concepts and Applications," Energies, vol. 18, no. 14, Art. no. 3660, 2025, doi: 10.3390/en18143660.
  12. J. Walther and M. Weigold, "A Systematic Review on Predicting and Forecasting the Electrical Energy Consumption in the Manufacturing Industry," Energies, vol. 14, no. 4, Art. no. 968, 2021, doi: 10.3390/en14040968.
  13. H. Li, D. Yang, H. Cao, W. Ge, E. Chen, X. Wen, and C. Li, "Data-driven hybrid Petri-net based energy consumption behaviour modelling for digital twin of energy-efficient manufacturing system," Energy, vol. 239, Art. no. 122178, 2022, doi: 10.1016/j.energy.2021.122178.
  14. C. Lai, Y. Wang, K. Fan, Q. Cai, Q. Ye, H. Pang, and X. Wu, "An improved forecasting model of short-term electric load of papermaking enterprises for production line optimization," Energy, vol. 245, Art. no. 123225, 2022, doi: 10.1016/j.energy.2022.123225.
  15. J. Cirera, J. A. Carino, D. Zurita, and J. A. Ortega, "Improving the Energy Efficiency of Industrial Refrigeration Systems by Means of Data-Driven Load Management," Processes, vol. 8, no. 9, Art. no. 1106, 2020, doi: 10.3390/pr8091106.
  16. B. Marchi, L. Bettoni, and S. Zanoni, "Assessment of Energy Efficiency Measures in Food Cold Supply Chains: A Dairy Industry Case Study," Energies, vol. 15, no. 19, Art. no. 6901, 2022, doi: 10.3390/en15196901.
  17. G. Arcidiacono, L. Ciulli, G. Pugliese, and C. Evangelisti, "A novel approach to energy management in the dairy industry using performance indicators and load profiles: Application to a cheese dairy plant in Tuscany, Italy," Energy, vol. 313, Art. no. 133240, 2024, doi: 10.1016/j.energy.2024.133240.
  18. M. Mostafaeipour, A. Kadkhoda, M. Rahimi, A. Mehrpooya, and H. Hosseini Dehshiri, "Optimal scheduling of a dairy industry based on energy hub considering renewable energy and ice storage," Journal of Cleaner Production, vol. 419, Art. no. 139580, 2023, doi: 10.1016/j.jclepro.2023.139580.
  19. A. Adeel, M. Apperley, and T. G. Walmsley, "An Interoperable User-Centred Digital Twin Framework for Sustainable Energy System Management," Energies, vol. 19, no. 2, Art. no. 333, 2026, doi: 10.3390/en19020333.
  20. International Organization for Standardization, ISO 23247-1:2021, Automation systems and integration - Digital twin framework for manufacturing - Part 1: Overview and general principles. Geneva, Switzerland: ISO, 2021.
  21. International Organization for Standardization, ISO 23247-2:2021, Automation systems and integration - Digital twin framework for manufacturing - Part 2: Reference architecture. Geneva, Switzerland: ISO, 2021.
  22. R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: OTexts, 2021. [Online]. Available: https://otexts.com/fpp3/

License

CCBY 4.0
Creative Commons Attribution 4.0 International

This work is openly licensed — share and adapt freely with attribution to the authors and the journal. View license terms ↗

Copyright (c) 2026 Андрій Гоєнко

§ 06 — Related

Similar articles in this journal

Related peer-reviewed studies published in this journal.
View all issues

DEVELOPMENT OF A DIGITAL TWIN OF AN ELEVATOR ELECTRIC DRIVE SYSTEM BASED ON THE STOCHASTIC ARIMAX MODEL

Stefan Zaichenko, Yevhen Filatov

Elevators are the most critical infrastructure elements of modern multi-storey buildings. The reliability of their electric drives directly affects passenger safety. The…

#digital twin #mathematical model #reliability #elevator electric drive
p. 112-118
10.20535/1813-5420.3.2026.359666

HIGH-RESPONSE DC MICROMOTORS: AN ANALYTICAL METHODOLOGY FOR SELECTING MAGNETIC LOADINGS AND ARMATURE ARCHITECTURE BY THE ELECTROMECHANICAL TIME-CONSTANT CRITERION

Mykhailo Kovalenko, Viktor Grebennikov, Andrii Stulishenko, Yevhen Ihnatiuk

The purpose of the study is to construct a closed, dimensionally consistent SI analytical methodology for estimating and minimizing the electromechanical time constant…

#DC micromotor #electromechanical time constant #dynamic response #magnetic loading
p. 83-88
10.20535/1813-5420.3.2026.369073