Models and methods for forecasting energy consumption in Russian economy until 2030

N.N. Volodina, M.V. Krotova

---

Abstract. In the modern global economy, energy resources such as gas and electricity play a critical role, profoundly impacting national economic stability, industrial performance, and public living standards. A review of the global energy market in the first half of the 21st century demonstrates that shifts
in energy availability can trigger crises, redistribute financial flows, compromise corporate
competitiveness, and reshape the global balance of power. Therefore, forecasting energy consumption (oil, gas, and electricity), both in natural units and in tons of oil equivalent (toe), is just as critical as conventional energy price forecasting.
The aim of this study is to analyze the Russian energy market and project energy consumption trends across key economic sectors.
Research methods. Statistical and systems analysis were used as the primary research methods, along
with frameworks for assessing geopolitical and geoeconomic impacts on the energy sector, time-series analysis, machine learning (ML), and neural networks.
Conclusions. As one of the world’s largest producers and exporters of oil, gas, and other energy resources, Russia cannot limit its national economy to the traditional trajectory of catch-up development typical of resource-exporting countries. Therefore, securing and continuously maintaining the nation’s technological and energy sovereignty is of paramount importanceThe practical significance of this study lies in the applicability of the developed models for evaluating, adjusting, and optimizing management decisions within the fuel and energy complex and other economic sectors.

Keywords: energy resources, energy consumption, price forecasting, strategic planning, economic sectors, energy conservation, energy efficiency

For citation. Volodina N.N., Krotova M.V. Models and methods for forecasting energy consumption in Russian economy until 2030. News of the Kabardino-Balkarian Scientific Center of RAS. 2026. Vol. 28. No. 3. Pp. 181–192. DOI: 10.35330/1991-6639-2026-28-3-181-192

©   Volodina N.N., Krotova M.V., 2026

References

1. Agashin A.V. Forecasting natural gas prices as a tool for reducing threats to Russia’s economic security. Modern Management Technologies. 2022. No. 4(100). P. 9. EDN: DACESS. (In Russian)
2. Bochkarev K.G. Forecasting electricity demand in the energy sector: problem description and solution. EnergyNet. 2023. No. 1-2(1). P. 27. DOI: 10.57112/E231-048. (In Russian)
3. Vertakova Yu.V. Review of economic approaches and models for GDP forecasting. Economics and Management. 2016. No. 2 (124). Pp. 22–29. EDN: VVJAUX. (In Russian)
4. Galperova E.V. Using a model bench for long-term forecasting of market demand for energy resources. Information and Mathematical Technologies in Science and Management. 2016. No. 4-2. Pp. 17–27. EDN: XCHSXV. (In Russian)
5. Drobysh I.I. Statistical models for forecasting prices in wholesale electricity markets: Russian and foreign experience. Bulletin of South Ural State University. Series: Economics and Management. 2017. Vol. 11. No. 3. Pp. 41–54. (In Russian)
6. Zolotova I.Yu., Dvorkin V.V. Short-term price forecasting in the Russian wholesale electricity market based on neural networks. Problems of Forecasting. 2017. No. 6. Pp. 47–57.
   EDN: YNJMGW. (In Russian)
7. Kaukin A.S., Pavlov P.N., Kosarev V.S. Short-term forecasting of electricity prices using generative neural networks. Business Informatics. 2023. Vol. 17. No. 3. Pp. 7–23. DOI: 10.17323/2587-814X.2023.3.7.23. (In Russian)
8. Lenin V.I. Imperializm kak vysshaya stadiya kapitalizma [Imperialism, the highest stage of capitalism]. Moscow: Politizdat, 1977. 136 p. (In Russian)
9. Leontyeva L.N. Selection of electricity price forecasting models. Machine Learning and Data Analysis. 2011. Vol. 1. No. 2. Pp. 127–137. EDN: OXWKUF. (In Russian)
10. Sidorova N.P., Demina D.S. Forecasting methods based on time series analysis. Information Technology Bulletin. 2017. No. 3(13). Pp. 118–126. EDN: ZIWDQP. (In Russian)
11. Suslov S.A., Kondratyev M.A., Sergeev K.V. Agent-based modeling as a tool for analyzing and forecasting energy demand. Problemy Upravleniya. 2010. No. 2. Pp. 46–52. EDN: MQHUHR. (In Russian)
12. Shikhina A.V., Yagodkina T.V. Improving accuracy of electricity price forecasting through the use of combined forecast models. Bulletin of Moscow Power Engineering Institute. 2020. No. 6. Pp. 119–128. DOI: 10.24160/1993-6982-2020-6-119-128. (In Russian)
13. Shchetinin E.Yu. Methods for modeling and forecasting spot prices for electricity. Financial Analytics: Problems and Solutions. 2008. No. 11. Pp. 78–83. EDN: JUDVZL. (In Russian)

Information about the authors

Natalia N. Volodina, Researcher, Institute of Economic Forecasting of the Russian Academy of Sciences;
47, Nakhimovsky prospekt, Moscow, 117418, Russia;
nn_volod@mail.ru, SPIN-code: 7914-1158
Maria V. Krotova, Candidate of Economic Sciences, Senior Researcher, Institute of Economic Forecasting of the Russian Academy of Sciences.
47, Nakhimovsky prospekt, Moscow, 117418, Russia;
mw_krotowa@mail.ru, SPIN-code: 7914-1158

Funding

The study was performed without external funding.