ПРОГНОЗИРОВАНИЕ ПОТРЕБЛЕНИЯ ЭЛЕКТРОЭНЕРГИИ ПРОМЫШЛЕННЫХ ПРЕДПРИЯТИЙ (ОБЗОР)
Ключевые слова:
Методы прогнозирования, краткосрочное прогнозирование электроэнергии, металлургическое предприятие, прогнозирование на сутки вперед, временные ряды
Аннотация
Крупные потребители электроэнергии в основном производят покупку электроэнергии на
оптовом рынке электроэнергии и мощности, например промышленные предприятия черной ме-
таллургии. Для производства продукции крупные промышленные предприятия ежедневно заказы-
вают почасовые объёмы потребления электроэнергии на двое суток вперёд, при необходимости за
сутки, предшествующие дню потребления, предприятия имеют право направлять скорректиро-
ванные значения. При этом за отклонения от плановых почасовых объёмов предприятия несут
дополнительные затраты, которые входят в тариф на электроэнергию. Одними из важнейших
факторов, которые влияют на прогнозирование почасового потребления электроэнергии, являют-
ся: многообразие видов основного и вспомогательного оборудования, мощностей потребителей
электроэнергии, осуществляющих технологические процессы предприятия; интенсивность за-
грузки производства и режимы работы в зависимости от производства сортамента; частое
использования часов максимальной электрической мощности в течение суток; энергоемкое произ-
водство продукции. Для построения прогнозных данных временных рядов строится модель про-
гнозирования почасового потребления электроэнергии промышленным предприятием и имеет
большое количество входных данных, которые имеют вероятностную составляющую. Рассмот-
рение различных методов прогнозирования временных рядов потребления электроэнергии про-
мышленных предприятий представляется актуальной научно-технической задачей. Это обуслов-
лено, требованиями минимизации, во-первых, скачков и сбоев в работе генерирующих мощностей
энергосистемы региона, в котором расположено предприятие (т.к. нагрузка, например, предпри-
ятий черной металлургии может достигает до 10% от общего потребления региона), а во-
вторых, дополнительных затрат, связанные с куплей/продажей объемов электроэнергии потреб-
ленной сверх заявки/невыбранной при неточном планировании почасовых объемов потребляемой
электроэнергии, которые входят в тариф на электроэнергию.
Литература
1. Efremenkova T.I. Issledovanie raskhoda elektroenergii na tekhnologicheskie tseli v
elektrostaleplavil'nom tsekhe metallurgicheskogo predpriyatiya metodami korrelyatsionnoregressionnogo
analiza [Study of electricity consumption for technological purposes in the electric
steelmaking shop of a metallurgical enterprise using correlation and regression analysis methods],
Sovremennye tekhnologii upravleniya [Modern control technologies], 2017, No 6 (78). ISSN2223-
9339. Available at: https://sovman.ru/article/7801/.
2. Mysik V.F., Zhdanov A.V. Resursy i podgotovka loma k plavke stali [Resources and preparation of
scrap for steel smelting]. 2nd ed. Ekaterinburg, 2017, 337 p.
3. Taskina A.O. Prognozirovanie tseny na elektroenergiyu na rynke «na sutki vpered» vo vtoroy tsenovoy
zone [Forecasting the price of electricity on the day-ahead market in the second price zone], 2020.
Available at: https://vital.lib.tsu.ru/vital/access/services/Download/vital:11747/SOURCE01.
4. Khank D.E., Uicheri D.U., Rayte A.Dzh. Biznes-prognozirovanie [Business forecasting]: transl. from
engl. 7th ed. Moscow: Vil'yams, 2003, 506 p.
5. Alberg D., Last M. Short-term load forecasting in smart meters with sliding window-based ARIMA
algorithms, Vietnam J. Comput. Sci., 2018, 5, pp. 241-249. Available at: https://doi.org/10.1007/
s40595-018-0119-7.
6. Rehan Jamil. Hydroelectricity consumption forecast for Pakistan using ARIMA modeling and supplydemand
analysis for the year 2030, Renewable Energy, 2020, Vol. 154, pp. 1-10. ISSN 0960-1481.
Available at: https://doi.org/10.1016/j.renene.2020.02.117.
7. Yuanyuan Wang, Jianzhou Wang, Ge Zhao, Yao Dong. Application of residual modification approach
in seasonal ARIMA for electricity demand forecasting: A case study of China, Energy Policy, 2012,
Vol. 48, pp. 284-294. ISSN 0301-4215. Available at: https://doi.org/10.1016/j.enpol.2012.05.026.
8. Xinbin Liang, Siliang Chen, Xu Zhu, Xinqiao Jin, Zhimin Du. Domain knowledge decomposition of
building energy consumption and a hybrid data-driven model for 24-h ahead predictions, Applied Energy,
2023, Vol. 344, 121244. ISSN 0306-2619. Available at: https://doi.org/10.1016/
j.apenergy.2023.121244.
9. Mehmet Bilgili, Engin Pinar. Gross electricity consumption forecasting using LSTM and SARIMA
approaches: A case study of Türkiye, Energy, 2023, Vol. 284, 128575. ISSN 0360-5442. Available at:
https://doi.org/10.1016/j.energy.2023.128575.
10. Russkov O.V. Metody prognozirovaniya neravnomernykh nestatsionarnykh vremennykh ryadov na
primere zadachi planirovaniya elektropotrebleniya promyshlennogo predpriyatiya [Methods for forecasting
uneven non-stationary time series using the example of the problem of planning electricity
consumption of an industrial enterprise], 2023. Available at: https://elib.spbstu.ru/dl/2/r23-
69.pdf/download/r23-69.pdf.
11. Nti I.K., Teimeh M., Nyarko-Boateng O. et al. Electricity load forecasting: a systematic review, Journal
of Electrical Systems and Inf. Technol., 2020, 7, 13. Available at: https://doi.org/10.1186/s43067-
020-00021-8.
12. Morgoeva A.D. Prognozirovanie potrebleniya elektricheskoy energii promyshlennym predpriyatiem s
pomoshch'yu metodov mashinnogo obucheniya [Forecasting the consumption of electrical energy by
an industrial enterprise using machine learning methods], Izvestiya Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov [Bulletin of Tomsk Polytechnic University. Georesources engineering],
2022, Vol. 333, No. 7, pp. 115-125. Available at: https://izvestiya.tpu.ru/archive/article/
view/3527/2751.
13. Morgoeva A.D., Morgoev I.D., Klyuev R.V., Khetagurov V.N., Gavrina O.A. Kratkosrochnoe
prognozirovanie elektropotrebleniya obogatitel'noy fabriki [Short-term forecasting of electricity consumption
of the processing plant], Gornyy informatsionno-analiticheskiy byulleten' [Mining information
and analytical bulletin], 2023, 5-1, pp. 157-169. Available at: https://www.giabonline.
ru/files/Data/2023/5/05_2023_157-169.pdf.
14. Klyuev R.V., Morgoeva A.D., Gavrina O.A., Bosikov I.I., Morgoev I.D. Prognozirovanie planovogo
potrebleniya elektroenergii dlya ob"edinennoy energosistemy s pomoshch'yu mashinnogo obucheniya
[Forecasting the planned electricity consumption for the unified power system using machine learning],
Zapiski Gornogo institute [Notes of the Mining Institute], 2023, No. 261. Available at:
https://cyberleninka.ru/article/n/prognozirovanie-planovogo-potrebleniya-elektroenergii-dlyaobedinennoy-
energosistemy-s-pomoschyu-mashinnogo-obucheniya.
15. Vyalkova S.A. Kratkosrochnoe prognozirovanie elektropotrebleniya Megapolisa na osnove ortogonal'nykh
razlozheniy i neyronnykh setey [Short-term forecasting of electricity consumption of a megalopolis based on
orthogonal decompositions and neural networks], 2022. Available at: https://www.npitu.
ru/upload/medialibrary/f39/hxsy86lrce075msy4mt96l1nvbqz4ux8/avtoreferat_vialkova.pdf?ysclid=lue3p
m3md4950760747.
16. Staroverov B.A. Teoreticheskoe obosnovanie i prakticheskaya realizatsiya sistem prognozirovaniya
elektropotrebleniya na osnove ansambley neyronnykh setey v masshtabe regional'noy setevoy kompanii
[Theoretical justification and practical implementation of power consumption forecasting systems based
on neural network ensembles on the scale of a regional grid company], 2023. Available at:
https://www.dissercat.com/content/teoreticheskoe-obosnovanie-i-prakticheskaya-realizatsiya-sistemprognozirovaniya-
elektropotr.
17. Alekseeva I.Yu. Kratkosrochnoe prognozirovanie elektropotrebleniya v elektroenergeticheskikh
sistemakh s ispol'zovaniem iskusstvennykh neyronnykh setey [Short-term forecasting of electricity
consumption in electric power systems using artificial neural networks]. Available at:
https://www.dissercat.com/content/kratkosrochnoe-prognozirovanie-elektropotrebleniya-velektroenergeticheskikh-
sistemakh-s-isp.
18. Zhen Shao, Qingru Zheng, Chen Liu, Shuangyan Gao, Gang Wang, Yan Chu. A feature extractionand
ranking-based framework for electricity spot price forecasting using a hybrid deep neural network,
Electric Power Systems Research, 2021, Vol. 200, 107453. ISSN 0378-7796. Available at:
https://doi.org/10.1016/j.epsr.2021.107453.
19. Bazhinov A.N. Metod prognozirovaniya ob"emov potrebleniya elektroenergii predpriyatiem chernoy
metallurgii na osnove neyro-nechetkikh algoritmov [Method for forecasting electricity consumption
volumes by a ferrous metallurgy enterprise based on neuro-fuzzy algorithms]. Available at:
https://www.dissercat.com/content/metod-prognozirovaniya-obemov-potrebleniya-elektroenergiipredpriyatiem-
chernoi-metallurgii-.
20. Khomutov S.O., Stashko V.I., Serebryakov N.A. Povyshenie tochnosti kratkosrochnogo
prognozirovaniya elektropotrebleniya grupp tochek postavki elektroenergii garantiruyushchikh
postavshchikov vtorogo urovnya [Improving the accuracy of short-term forecasting of electricity consumption
of groups of electricity supply points of second-tier guaranteed suppliers], Izvestiya
Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov [Bulletin of Tomsk Polytechnic
University. Georesources engineering], 2020, Vol. 331, No. 6, pp. 128-140. Available at:
https://doi.org/10.18799/24131830/2020/6/2682.
21. Chuang Li, Guojie Li, Keyou Wang, Bei Han. Short-term electrical load forecasting based on error
correction using dynamic mode decomposition, Applied Energy, March 2020, Vol. 261, 114368.
Available at: https://www.sciencedirect.com/science/article/abs/pii/S0306261919320550? via%3Dihub.
22. Taylor J.W., McSharry P.E. Short-term load forecasting methods: An evaluation based on European data,
IEEE Transactions on Power Systems, November 2007, Vol. 22, Issue 4, pp. 2213-2219. ISSN
08858950. Available at: https://www.scopus.com/record/display.uri?eid=2-s2.0-36348992080&origin=
inward&txGid=21e6fb2c3300889b3ff56d705b52239d.
23. Phillip G. Gould, Anne B. Koehler, J. Keith Ord, Ralph D. Snyder, Rob J. Hyndman, Farshid Vahid-
Araghi. Forecasting time series with multiple seasonal patterns, European Journal of Operational Research,
2008, Vol. 191, Issue 1, pp. 207-222. ISSN 0377-2217, Available at: https://doi.org/10.1016/
j.ejor.2007.08.024.
24. Korotkevich M.A., Kurachinskiy V.V. Prognozirovanie elektricheskoy nagruzki energosistemy na
sleduyushchie sutki s ispol'zovaniem metoda iskusstvennykh neyronnykh setey [Forecasting the electrical
load of the power system for the next day using the method of artificial neural networks],
Energetika. Izvestiya vysshikh uchebnykh zavedeniy i energeticheskikh ob"edineniy SNG [Power Engineering.
News of higher educational institutions and energy associations of the CIS], 2010, No. 2. Available at: https://cyberleninka.ru/article/n/prognozirovanie-elektricheskoy-nagruzki-energosistemyna-
sleduyuschie-sutki-s-ispolzovaniem-metoda-iskusstvennyh-neyronnyh-setey.
25. Chernetsov V.I., Kazakovskiy E.N. Prognozirovanie potrebleniya elektricheskoy energii s
ispol'zovaniem neyronnykh setey [Forecasting the consumption of electrical energy using neural networks],
NiKa [NiKa], 2006. Available at: https://cyberleninka.ru/article/n/prognozirovaniepotrebleniya-
elektricheskoy-energii-s-ispolzovaniem-neyronnyh-setey.
26. Jinliang Zhang, Yi-Ming Wei, Dezhi Li, Zhongfu Tan, Jianhua Zhou. Short term electricity load forecasting
using a hybrid model, Energy, 2018, Vol. 158, pp. 774-781. ISSN 0360-5442,
https://doi.org/10.1016/j.energy.2018.06.012.
27. Staroverov B.A. Teoreticheskoe obosnovanie i prakticheskaya realizatsiya sistem prognozirovaniya
elektropotrebleniya na osnove ansambley neyronnykh setey v masshtabe regional'noy setevoy
kompanii [Theoretical justification and practical implementation of electricity consumption forecasting
systems based on neural network ensembles on the scale of a regional grid company], 2023. Available
at: https://www.dissercat.com/content/teoreticheskoe-obosnovanie-i-prakticheskaya-realizatsiyasistem-
prognozirovaniya-elektropotr.
elektrostaleplavil'nom tsekhe metallurgicheskogo predpriyatiya metodami korrelyatsionnoregressionnogo
analiza [Study of electricity consumption for technological purposes in the electric
steelmaking shop of a metallurgical enterprise using correlation and regression analysis methods],
Sovremennye tekhnologii upravleniya [Modern control technologies], 2017, No 6 (78). ISSN2223-
9339. Available at: https://sovman.ru/article/7801/.
2. Mysik V.F., Zhdanov A.V. Resursy i podgotovka loma k plavke stali [Resources and preparation of
scrap for steel smelting]. 2nd ed. Ekaterinburg, 2017, 337 p.
3. Taskina A.O. Prognozirovanie tseny na elektroenergiyu na rynke «na sutki vpered» vo vtoroy tsenovoy
zone [Forecasting the price of electricity on the day-ahead market in the second price zone], 2020.
Available at: https://vital.lib.tsu.ru/vital/access/services/Download/vital:11747/SOURCE01.
4. Khank D.E., Uicheri D.U., Rayte A.Dzh. Biznes-prognozirovanie [Business forecasting]: transl. from
engl. 7th ed. Moscow: Vil'yams, 2003, 506 p.
5. Alberg D., Last M. Short-term load forecasting in smart meters with sliding window-based ARIMA
algorithms, Vietnam J. Comput. Sci., 2018, 5, pp. 241-249. Available at: https://doi.org/10.1007/
s40595-018-0119-7.
6. Rehan Jamil. Hydroelectricity consumption forecast for Pakistan using ARIMA modeling and supplydemand
analysis for the year 2030, Renewable Energy, 2020, Vol. 154, pp. 1-10. ISSN 0960-1481.
Available at: https://doi.org/10.1016/j.renene.2020.02.117.
7. Yuanyuan Wang, Jianzhou Wang, Ge Zhao, Yao Dong. Application of residual modification approach
in seasonal ARIMA for electricity demand forecasting: A case study of China, Energy Policy, 2012,
Vol. 48, pp. 284-294. ISSN 0301-4215. Available at: https://doi.org/10.1016/j.enpol.2012.05.026.
8. Xinbin Liang, Siliang Chen, Xu Zhu, Xinqiao Jin, Zhimin Du. Domain knowledge decomposition of
building energy consumption and a hybrid data-driven model for 24-h ahead predictions, Applied Energy,
2023, Vol. 344, 121244. ISSN 0306-2619. Available at: https://doi.org/10.1016/
j.apenergy.2023.121244.
9. Mehmet Bilgili, Engin Pinar. Gross electricity consumption forecasting using LSTM and SARIMA
approaches: A case study of Türkiye, Energy, 2023, Vol. 284, 128575. ISSN 0360-5442. Available at:
https://doi.org/10.1016/j.energy.2023.128575.
10. Russkov O.V. Metody prognozirovaniya neravnomernykh nestatsionarnykh vremennykh ryadov na
primere zadachi planirovaniya elektropotrebleniya promyshlennogo predpriyatiya [Methods for forecasting
uneven non-stationary time series using the example of the problem of planning electricity
consumption of an industrial enterprise], 2023. Available at: https://elib.spbstu.ru/dl/2/r23-
69.pdf/download/r23-69.pdf.
11. Nti I.K., Teimeh M., Nyarko-Boateng O. et al. Electricity load forecasting: a systematic review, Journal
of Electrical Systems and Inf. Technol., 2020, 7, 13. Available at: https://doi.org/10.1186/s43067-
020-00021-8.
12. Morgoeva A.D. Prognozirovanie potrebleniya elektricheskoy energii promyshlennym predpriyatiem s
pomoshch'yu metodov mashinnogo obucheniya [Forecasting the consumption of electrical energy by
an industrial enterprise using machine learning methods], Izvestiya Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov [Bulletin of Tomsk Polytechnic University. Georesources engineering],
2022, Vol. 333, No. 7, pp. 115-125. Available at: https://izvestiya.tpu.ru/archive/article/
view/3527/2751.
13. Morgoeva A.D., Morgoev I.D., Klyuev R.V., Khetagurov V.N., Gavrina O.A. Kratkosrochnoe
prognozirovanie elektropotrebleniya obogatitel'noy fabriki [Short-term forecasting of electricity consumption
of the processing plant], Gornyy informatsionno-analiticheskiy byulleten' [Mining information
and analytical bulletin], 2023, 5-1, pp. 157-169. Available at: https://www.giabonline.
ru/files/Data/2023/5/05_2023_157-169.pdf.
14. Klyuev R.V., Morgoeva A.D., Gavrina O.A., Bosikov I.I., Morgoev I.D. Prognozirovanie planovogo
potrebleniya elektroenergii dlya ob"edinennoy energosistemy s pomoshch'yu mashinnogo obucheniya
[Forecasting the planned electricity consumption for the unified power system using machine learning],
Zapiski Gornogo institute [Notes of the Mining Institute], 2023, No. 261. Available at:
https://cyberleninka.ru/article/n/prognozirovanie-planovogo-potrebleniya-elektroenergii-dlyaobedinennoy-
energosistemy-s-pomoschyu-mashinnogo-obucheniya.
15. Vyalkova S.A. Kratkosrochnoe prognozirovanie elektropotrebleniya Megapolisa na osnove ortogonal'nykh
razlozheniy i neyronnykh setey [Short-term forecasting of electricity consumption of a megalopolis based on
orthogonal decompositions and neural networks], 2022. Available at: https://www.npitu.
ru/upload/medialibrary/f39/hxsy86lrce075msy4mt96l1nvbqz4ux8/avtoreferat_vialkova.pdf?ysclid=lue3p
m3md4950760747.
16. Staroverov B.A. Teoreticheskoe obosnovanie i prakticheskaya realizatsiya sistem prognozirovaniya
elektropotrebleniya na osnove ansambley neyronnykh setey v masshtabe regional'noy setevoy kompanii
[Theoretical justification and practical implementation of power consumption forecasting systems based
on neural network ensembles on the scale of a regional grid company], 2023. Available at:
https://www.dissercat.com/content/teoreticheskoe-obosnovanie-i-prakticheskaya-realizatsiya-sistemprognozirovaniya-
elektropotr.
17. Alekseeva I.Yu. Kratkosrochnoe prognozirovanie elektropotrebleniya v elektroenergeticheskikh
sistemakh s ispol'zovaniem iskusstvennykh neyronnykh setey [Short-term forecasting of electricity
consumption in electric power systems using artificial neural networks]. Available at:
https://www.dissercat.com/content/kratkosrochnoe-prognozirovanie-elektropotrebleniya-velektroenergeticheskikh-
sistemakh-s-isp.
18. Zhen Shao, Qingru Zheng, Chen Liu, Shuangyan Gao, Gang Wang, Yan Chu. A feature extractionand
ranking-based framework for electricity spot price forecasting using a hybrid deep neural network,
Electric Power Systems Research, 2021, Vol. 200, 107453. ISSN 0378-7796. Available at:
https://doi.org/10.1016/j.epsr.2021.107453.
19. Bazhinov A.N. Metod prognozirovaniya ob"emov potrebleniya elektroenergii predpriyatiem chernoy
metallurgii na osnove neyro-nechetkikh algoritmov [Method for forecasting electricity consumption
volumes by a ferrous metallurgy enterprise based on neuro-fuzzy algorithms]. Available at:
https://www.dissercat.com/content/metod-prognozirovaniya-obemov-potrebleniya-elektroenergiipredpriyatiem-
chernoi-metallurgii-.
20. Khomutov S.O., Stashko V.I., Serebryakov N.A. Povyshenie tochnosti kratkosrochnogo
prognozirovaniya elektropotrebleniya grupp tochek postavki elektroenergii garantiruyushchikh
postavshchikov vtorogo urovnya [Improving the accuracy of short-term forecasting of electricity consumption
of groups of electricity supply points of second-tier guaranteed suppliers], Izvestiya
Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov [Bulletin of Tomsk Polytechnic
University. Georesources engineering], 2020, Vol. 331, No. 6, pp. 128-140. Available at:
https://doi.org/10.18799/24131830/2020/6/2682.
21. Chuang Li, Guojie Li, Keyou Wang, Bei Han. Short-term electrical load forecasting based on error
correction using dynamic mode decomposition, Applied Energy, March 2020, Vol. 261, 114368.
Available at: https://www.sciencedirect.com/science/article/abs/pii/S0306261919320550? via%3Dihub.
22. Taylor J.W., McSharry P.E. Short-term load forecasting methods: An evaluation based on European data,
IEEE Transactions on Power Systems, November 2007, Vol. 22, Issue 4, pp. 2213-2219. ISSN
08858950. Available at: https://www.scopus.com/record/display.uri?eid=2-s2.0-36348992080&origin=
inward&txGid=21e6fb2c3300889b3ff56d705b52239d.
23. Phillip G. Gould, Anne B. Koehler, J. Keith Ord, Ralph D. Snyder, Rob J. Hyndman, Farshid Vahid-
Araghi. Forecasting time series with multiple seasonal patterns, European Journal of Operational Research,
2008, Vol. 191, Issue 1, pp. 207-222. ISSN 0377-2217, Available at: https://doi.org/10.1016/
j.ejor.2007.08.024.
24. Korotkevich M.A., Kurachinskiy V.V. Prognozirovanie elektricheskoy nagruzki energosistemy na
sleduyushchie sutki s ispol'zovaniem metoda iskusstvennykh neyronnykh setey [Forecasting the electrical
load of the power system for the next day using the method of artificial neural networks],
Energetika. Izvestiya vysshikh uchebnykh zavedeniy i energeticheskikh ob"edineniy SNG [Power Engineering.
News of higher educational institutions and energy associations of the CIS], 2010, No. 2. Available at: https://cyberleninka.ru/article/n/prognozirovanie-elektricheskoy-nagruzki-energosistemyna-
sleduyuschie-sutki-s-ispolzovaniem-metoda-iskusstvennyh-neyronnyh-setey.
25. Chernetsov V.I., Kazakovskiy E.N. Prognozirovanie potrebleniya elektricheskoy energii s
ispol'zovaniem neyronnykh setey [Forecasting the consumption of electrical energy using neural networks],
NiKa [NiKa], 2006. Available at: https://cyberleninka.ru/article/n/prognozirovaniepotrebleniya-
elektricheskoy-energii-s-ispolzovaniem-neyronnyh-setey.
26. Jinliang Zhang, Yi-Ming Wei, Dezhi Li, Zhongfu Tan, Jianhua Zhou. Short term electricity load forecasting
using a hybrid model, Energy, 2018, Vol. 158, pp. 774-781. ISSN 0360-5442,
https://doi.org/10.1016/j.energy.2018.06.012.
27. Staroverov B.A. Teoreticheskoe obosnovanie i prakticheskaya realizatsiya sistem prognozirovaniya
elektropotrebleniya na osnove ansambley neyronnykh setey v masshtabe regional'noy setevoy
kompanii [Theoretical justification and practical implementation of electricity consumption forecasting
systems based on neural network ensembles on the scale of a regional grid company], 2023. Available
at: https://www.dissercat.com/content/teoreticheskoe-obosnovanie-i-prakticheskaya-realizatsiyasistem-
prognozirovaniya-elektropotr.
