On the choice of the method of dynamic rationing of energy resources in oil refineries

The article discusses the possibility of calculating the expected energy demand based on big data and machine learning for the energy technological processes in oil refineries. In order to obtain predictive data, linear regression, machine learning, and neural networks are proposed to be used to build a mathematical model. The advantages and disadvantages of these methods are discussed, and the accuracy of the models is compared with the possibility of interpreting them. Thanks to the use of advanced statistical methods, the variability of energy consumption can be interpreted through factor analysis. Through pilot tests, the practical significance of these proposed methods for their practical use in an energy management system is demonstrated, as well as the transition to statistical control of the process.

1. Kalinina N. M., Kulik N. A. Otsenka stepeni innovatsionnoy gotovnosti sistemnoy transformatsii menedzhmenta v usloviyakh perekhoda k shestomu tekhnologicheskomu ukladu [Assessing the degree of innovative readiness of systemic transformation of management in the context of transition to the sixth technological paradigm] // Omskiy nauchnyy vestnik. Ser. Obshchestvo. Istoriya. Sovremennost’. Omsk Scientific Bulletin. Series Society. History. Modernity. 2023. Vol. 8, no. 4. P. 139–145. DOI: 10.25206/2542-0488-2023-8-4-139-145. EDN: VVVAXR. (In Russ.).

2. Khakimov R. A. Identifikatsiya matematicheskoy modeli protsessa gidroochistki dizel’nogo topliva dlya sozdaniya sistemy optimizatsii gruppy tekhnologicheskikh ustanovok neftepererabatyvayushchego zavoda [Identification of mathematical model of diesel fuel hydrotreatment process for creation system optimization of group of technological units of oil refinery plant] // Omskiy nauchnyy vestnik. Omsk Scientific Bulletin. 2018. No. 4 (160). P. 174–178. DOI: 10.25206/1813-8225-2018-160-174-178. (In Russ.).

3. Kudriashov N. S. Dynamic energy consumption rationing based on machine learning algorithms for oil refining tasks // Computing, Telecommunications and Control. 2021. Vol. 14, no. 3. P. 20–32. DOI: 10.18721/JCSTCS.14302. (In Engl.).

4. Goldratt E. M., Cox J. Tsel’. Protsess nepreryvnogo sovershenstvovaniya [The Goal. A Process of Ongoing Improvement] / trans. from Engl. P. Samsonov. Moscow, 2023. 400 p. (In Russ.).

5. Adler Yu. P., Shper V. L. Prakticheskoye rukovodstvo po statisticheskomu upravleniyu protsessami [Practical guide to statistical process management]. Moscow, 2019. 234 p. (In Russ.).

6. Faktornyy analiz [Factor analysis]. URL: https://masters.donntu.ru/2007/kita/bolkunevich/library/fakt.htm (accessed: 12.03.2024). (In Russ.).

7. Dolzhenko R. A. Sushchnost’ i otsenka effektivnosti ispol’zovaniya optimizatsionnykh tekhnologiy «Lin» i «Shest’ sigm» [Essence and evaluation of optimizational technologies «Lean» and «Six Sigma»] // Vestnik Omskogo universiteta. Seriya «Ekonomika». Herald of Omsk University. Series «Economics». 2014. No. 1. P. 25–33. EDN: SFORMX. (In Russ.).

8. Gigi K., DeCarlo N., Williams B. Shest’ sigm dlya chaynikov [Six sigma for dummies] / trans. from Engl. and ed. A. Yu. Zayakina. Moscow, 2008. 320 p. (In Russ.).

9. Rezanov E. M., Starikov A. P., Finichenko A. Yu., Kushnarenko A. V. Ob effektivnosti regulirovaniya vysokotemperaturnogo agregata neftepererabatyvayushchego zavoda [On the efficiency of control of the high-temperature unit of the oil refinery] // Energosberezheniye i vodopodgotovka. Energy Saving and Water Treatment. 2023. No. 5 (145). P. 15–19. EDN: BXYMRV. (In Russ.).

10. Danilov O. L., Garyaev A. B., Yakovlev I. V. Energosberezheniye v teploenergetike i teplotekhnologiyakh [Energy saving in thermal power engineering and thermal technologies]. Moscow, 2017. 424 p. (In Russ.)

11. Bereznyak I. S., Gusarova O. M., Popova V. V. Matematicheskoye modelirovaniye s ispol’zovaniyem tsifrovykh tekhnologiy v reshenii prikladnykh zadach analiza dannykh [Math modeling with the use of digital technologies in solving application tasks of data analysis] //sovremennyye naukoyemkiye tekhnologii. Modern High Technologies. 2023. No. 12-1. P. 10–15. DOI: 10.17513/snt.39853. EDN: NFNNZH. (In Russ.).

12. Herawati N. A., Gary A. A. P., Hikmawati E. [et al.]. A Hybrid Predictive Model as an Emission Reduction Strategy Based on Power Plants’ Fuel Consumption Activity // IEEE Access. DOI: 10.1109/ACCESS.2024.3380809. (In Engl.).

13. de Myttenaere A., Golden B., Le Grand B. [et al.]. Mean absolute percentage error for regression models // Neurocomputing. 2016. Vol. 192. P. 38–48. DOI: 10.1016/j.neucom.2015.12.114. (In Engl.).

14. Hu Z., Jin Y., Hu Q. [et al.]. Prediction of Fuel Consumption for Enroute Ship Based on Machine Learning // IEEE Access. 2019. Vol. 7. P. 119497–119505. DOI: 10.1109/ACCESS.2019.2933630. (In Engl.).

15. Nawaz M., Maulud A. S., Zabiri H. [et al.]. Review of Multiscale Methods for Process Monitoring, With an Emphasis on Applications in Chemical Process Systems // IEEE Access. 2022. Vol. 10. P. 49708–49724. DOI: 10.1109/ACCESS.2022.3171907. (In Engl.).

16. Klyachkin V. N. Modeli i metody statisticheskogo kontrolya mnogoparametricheskogo tekhnologicheskogo protsessa [Models and methods of statistical control of a multiparametric technological process]. Ulyanovsk, 2004. 284 p. (In Russ.).