THE USE OF INTERNET OF THINGS TECHNOLOGY IN THE ENERGY INDUSTRY OF OSC MINSK AUTOMOBILE PLANT

Abstract

The aim of the study is to develop a modelling approach for quantifying the potential effect of IoT solutions on the consumption of fuel and energy resources, the energy intensity of products, and the investment efficiency of an automotive enterprise. An analysis is carried out of the state of the energy-saving problem in the automotive industry abroad, where the Internet of Things (IoT) technology is considered a key tool for creating intelligent energy management systems at automobile plants. The literature emphasizes that modern IoT solutions provide a transition from reactive to predictive and optimization-based energy management, and that a promising direction is the integration of Industrial Internet of Things (IIoT) with artificial intelligence algorithms for forecasting energy consumption and optimizing the operating modes of energy-intensive equipment; in this study such AI components are considered only as part of the review of international experience and are not included in the methodology used by the authors.

The regulatory framework of the research is the State Program “Energy Saving” for 2021–2025. A mathematical model is presented for assessing the effect of introducing Internet of Things (IoT) technology into the energy management system of JSC “Minsk Automobile Plant”, based on a comparison of scenarios without IoT and with IoT. The model uses official aggregated data on energy saving at MAZ for 2024–2025 and makes it possible, in a calculated form, to estimate the potential annual savings in energy costs, changes in specific energy costs, and investment efficiency indicators, including net present value and payback period, under the assumption of digitalization of the energy management system. The individual contribution of IoT solutions to the achieved energy-saving indicators is not distinguished in the available sources, therefore the model uses aggregated coefficients that reflect the combined effect of the implemented measures.

The modelling results show that, under realistic cost parameters and reduction coefficients calibrated to the aggregated energy-saving indicators of MAZ, the potential reduction in annual energy consumption in the IoT scenario is comparable to the actually achieved values and provides a positive financial outcome with an acceptable payback period. The proposed modelling approach can be used for indicative justification of investments in the IoT infrastructure of the energy management system at machine-building enterprises, taking into account that the contribution of IoT solutions is not singled out separately in the source data and is assessed in an aggregated manner.