Variant regression modeling of electricity production in the Russian Federation

Objective. The aim of the study is to build a linear regression model of electricity generation in the Russian Federation depending on resource indicators, which include: the volume of coal and gas production, the production of fuel oil. Statistical data for 2005 - 2020 were used as the information base of the study.

Method. Estimation of unknown parameters of the linear model is carried out using three methods - least squares, modules and anti-robust estimation. They behave differently with respect to outliers in the data. The second of them does not react to outliers at all, completely ignoring them, and the third, on the contrary, strongly gravitates towards them, therefore, these methods are a kind of antagonists in relation to each other.

Result. Three alternative models of a linear regression model of electricity production with high accuracy are obtained. The value of the parametric stability index of the data sample, based on the properties of the parameter estimation methods, is calculated. Observations are identified that correspond to the maximum and minimum extent to the linear model on the analyzed sample. The values of the contributions of the factors to the right parts of the models are calculated.

Conclusion. Three versions of the model built by different methods can be successfully used to solve problems related to forecasting the production of electricity in the country. At the same time, the variant constructed by the least squares method is a kind of compromise.

1. Meng M., Sanders K.T. A data-driven approach to investigate the impact of air temperature on the efficiencies of coal and natural gas generators.Applied Energy. 2019;253:113486.

2. Adebisi O.I., Adejumobi I.A. Development of a Load Management Scheme for the Nigerian Deregulated Electricity Market Using Regression Model. IEEE PES/IAS Power Africa Conference: Power Economics and Energy Innovation in Africa, Power Africa. 2019; 8928928: 682-687.

3. SağlamÜ. Assessment of the productive efficiency of large wind farms in the United States: An application of two-stage data envelopment analysis. Energy, Conversion and Management. 2017; 153:. 188-214.

4. Ke Y., Yang X., Xiong Y., Liang X. Power generation dispatching for environmental protection based on recursive neural network and ant colony optimization algorithm. Information and Control. 2017; 46(4): 415-421.

5. Mokhov V.G., Demyanenko T.S. Determination of significant factors in forecasting the volume of electricity consumption in the unified energy system of the Urals based on regression analysis. Vestnik UrFU. Series: Economics and Management. 2017; 16(4): 642-662. [In Russ]

6. Zueva V.N. Regression methods for predicting the load schedule of electrical equipment. Polythematic network electronic scientific journal of the Kuban State Agrarian University. 2017; 126: 119-130. [In Russ]

7. Stennikov V.A., Dobrovolskaya T.V. Methods of regression analysis in studies of heat consumption in Russia. Bulletin of the Russian University of Economics named after G.V. Plekhanov. 2018; 2 (98):. 142- 153. [In Russ]

8. Official portal of the Federal State Statistics Service. [Electronic resource] URL: https://rosstat.gov.ru (date of access: 12/21/2022). [In Russ]

9. Site of statistics and analytics: World finance. Gas production. [Electronic resource] URL: http://globalfinances.ru/dobycha-gaza-v-rossii-po-godam/ (date of access: 12/21/2022). [In Russ]

10. Site of statistics and analytics: World finance. Coal mining. [Electronic resource] URL: http://globalfinances.ru/dobycha-uglya-v-rossii-po-godam/ (date of access: 12/19/2022). [In Russ]

11. Official website of the Ministry of Energy of the Russian Federation (Ministry of Energy of Russia). [Electronic resource] URL: https://minenergo.gov.ru/node/1212 (date of access: 12/21/2022). [In Russ]

12. Showcase of statistical data statistics. [Electronic resource] URL: https://showdata.gks.ru/finder (date of access: 2.12.2022). [In Russ]

13. Official portal of the Unified Interdepartmental Information and Statistical System (EMISS). [Electronic resource] URL: https://www.fedstat.ru/ (date of access: 12/21/2022). [In Russ]

14. Demidenko E.Z. Linear and non-linear regression. M.: Finance and statistics. 1981;302. [In Russ]

15. Noskov S.I. On the method of mixed estimation of linear regression parameters. Information technology and mathematical modeling in the management of complex systems. 2019; 1:14-20. [In Russ]

16. S. I. Noskov. “An anti-robust estimation method for linear regression parameters: the number of approximation errors that are maximal in modulus,” South Siberian Scientific Bulletin. 2020;1:51-54. [In Russ]

17. Noskov S.I. Discrete model of aluminum production in the Russian Federation. Bulletin of the Technological University. 2022;25( 2):80-82. [In Russ]

18. Noskov S.I. Index of parametric stability of the regression model. Bulletin of transport of the Volga region. 2021; 2 (86): 74-77. [In Russ]

19. Noskov S. I., Ilyushonok D. M. An approach to clustering a data sample based on the method of least modules. South Siberian Scientific Bulletin. 2020; 6: 255-259. [In Russ]

20. Noskov S.I. Evaluation of the dynamics of the contributions of factors in a linear regression model. Bulletin of the Voronezh State Technical University. 2021;17( 5):15-19. [In Russ]