OPTIMIZATION OF THE STRUCTURE OF THE ENERGY CONSUMPTION FORECASTING SYSTEM WITH ATYPICAL ENERGY CONSUMPTION PATTERNS
Abstract
The creation of an intelligent energy consumption forecasting device for consumers with atypical
energy consumption is considered, depending on the required forecast accuracy, taking into account, in
addition to the target parameters of the power grid (P, Q), technological processes of enterprises, influencing
factors: socio-economic (hour of the day; day of the week; ordinal number of the day in the year;
sign of a holiday or mass events d); meteorological: (wind-cold index). The model refers to intelligent devices for adaptive forecasting of power consumption modes of the electric grid based on a multilayer
neural network. The article is devoted to the choice of the optimal architecture of the neural network (NN)
and the method of its training, providing forecasting with the least error. A multifactional model of power
consumption based on a multilayer NN has been synthesized and tested. Within the framework of the conducted
research, an NN model was built describing the architecture of a cyber-physical system (CFS) for
forecasting power consumption. It has been established that for each consumer, due to significant differences
in the nature of energy consumption, it is necessary to experimentally select network parameters in
order to achieve a minimum prediction error. It is shown that with atypical power consumption, i.e., not
repeated over time periods (hour, day, week, etc.), artificial intelligence and deep machine learning methods
are an effective tool for solving poorly formalized or non-formalized tasks. The developed model has
acceptable accuracy (MSE deviation up to 15%). To increase the accuracy of the forecast, it is necessary
to carry out a regular refinement of the model and adjust it to the actual situation, taking into account new
additive factors affecting the electricity consumption curve. The possibility of using this device in the technological
management systems of regional grid companies, which forms the basis of a hierarchical automated
information measuring system for monitoring and accounting for electricity, by accounting and
forecasting the active and reactive power of electric consumers
References
gosudarstvennoy programmy Rossiyskoy Federatsii "Energosberezhenie i povyshenie energeticheskoy
effektivnosti". Razmeshchen v SPS "Konsul'tant Plyus" [Decree of the Government of the Russian
ederation of September 9, 2023 N 1473 “On approval of the comprehensive state program of the
Russian ederation “Energy saving and increasing energy efficiency”. Posted in the ATP “ onsultant
Plus”. – https://base.garant.ru/407632842/]. Available at: https://base.garant.ru/407632842/.
2. Poluyanovich N.K. Montazh, naladka, ekspluatatsiya i remont sistem elektrosnabzheniya
promyshlennykh predpriyatiy. Dopushcheno UMO po obrazovaniyu v oblasti energetiki i
elektrotekhniki v kachestve uchebnogo posobiya dlya studentov vysshikh uchebnykh zavedeniy,
obuchayushchikhsya po spetsial'nosti 140610 – «Elektrooborudovanie i elektrokhozyaystvo
predpriyatiy, organizatsiy i uchrezhdeniy» napravleniya podgotovki 140600 – «Elektrotekhnika,
elektromekhanika i elektro-tekhnologii». Ser. uchebniki dlya vuzov. Spetsial'naya literature [Installation,
adjustment, operation and repair of power supply systems for industrial enterprises. The educational
educational institution for education in the field of energy and electrical engineering has been
approved as a teaching aid for students of higher educational institutions studying in the specialty
140610 – “Electrical equipment and electrical equipment of enterprises, organizations and institutions”
in the direction of training 140600 – “Electrical engineering, electromechanics and electrical technology”.
Ser. textbooks for universities. Special literature]. 3rd ed. Saint Petersburg, 2017.
3. Poluyanovich N.K., Tibeyko I.A. Ekspluatatsiya i remont sistem elektrosnabzheniya promyshlennykh
predpriyatiy [Operation and repair of power supply systems of industrial enterprises]. Taganrog, 2014.
4. Shurykin A.A., Poluyanovich N.K. Otsenka matematicheskogo ozhidaniya resursa izolyatsii v
zadachakh povysheniya nadezhnosti elektrooborudovaniya [Estimation of the mathematical expectation
of insulation life in problems of increasing the reliability of electrical equipment], Inzhenernyy
vestnik Dona [Engineering Bulletin of the Don], 2019, No. 2 (53), pp. 16.
5. Dubyago M.N., Poluyanovich N.K., Bur'kov D.V. Razrabotka metoda prognozirovaniya protsessa
stareniya izolyatsii na osnove termofluktuatsionnoy teorii chastichnykh razryadov [Development of a
method for predicting the aging process of insulation based on the thermal fluctuation theory of partial
discharges], Inzhenernyy vestnik Dona [Engineering Bulletin of the Don], 2017, No. 3 (46), pp. 26.
6. Serebryakov N.A., Khomutov S.O. Analiz sluchaynoy sostavlyayushchey vremennogo ryada
elektricheskoy nagruzki gruppy tochek postavki elektroenergii sel'khozproizvoditeley [Analysis of the
random component of the time series of electrical load of a group of electricity supply points for agricultural
producers], Vestnik Altayskogo gosudarstvennogo agrarnogo universiteta [Bulletin of the Altai
State Agrarian University], 2019, No. 5 (175), pp. 153-158.
7. Dubyago M.N., Poluyanovich N.K. Nerazrushayushchiy metod prognozirovaniya ostatochnogo resursa
silovykh kabel'nykh liniy [Non-destructive method for predicting the residual life of power cable
lines], Informatika, vychislitel'naya tekhnika i inzhenernoe obrazovanie [Informatics, computer technology
and engineering education], 2012, No. 1 (8), pp. 27-33.
8. Poluyanovich N.K., Dubyago M.N. Otsenka vozdeystvuyushchikh faktorov i prognozirovanie
elektropotrebleniya v regional'noy energosisteme s uchetom rezhima ee ekspluatatsii [Assessment of
influencing factors and forecasting of electricity consumption in the regional energy system taking into
account its operating mode], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering
Sciences], 2022, No. 2 (226), pp. 31-46.
9. Rudakov E., Saakyan Yu., Nigmatulin B., Prokhorova N. Tsena rastochitel'nosti [The price of wastefulness],
Ekspert [Expert]. Iyun' 2008, pp. 24.
10. Bilalova A.I. Razrabotka modeley prognozirovaniya v sfere energosberezheniya [Development of
forecasting models in the field of energy saving], Sb. nauchnykh trudov mezhdunarodnoy nauchnotekhnicheskoy
konferentsii studentov i molodykh uchenykh «Molodezh'. Nauka. Tekhnologii (MNTK-
2017)» [Collection of scientific papers of the international scientific and technical conference of students
and young scientists “Youth. The science. Technologies (MNTK-2017)"]. Novosibirsk, 2017,
pp. 11-15.
11. Bilalova A.I. Statistika potrebleniya elektroenergii v g. Ul'yanovsk [Statistics of electricity consumption
in Ulyanovsk], Vuzovskaya nauka v sovremennykh usloviyakh: Sb. materialov 48-y nauchnotekhnicheskoy
konferentsii [University science in modern conditions: Collection of materials of the
48th scientific and technical conference]. Ul'yanovsk: UlGTU, 2013, pp. 15-18.
12. Domanov V.I., Bilalova A.I. Prognozirovanie ob"emov energopotrebleniya v zavisimosti ot iskhodnoy
informatsii [Forecasting the volume of energy consumption depending on the initial information],
Vestnik YuUrGU. Seriya «Energetika» [Bulletin of SUSU. Series "Energy"], 2016, Vol. 16, No. 2,
pp. 59-65. DOI: 10.14529/power160208.
13. Kudrin B.I., Mozgalin A.V. Metodika obespecheniya pochasovogo prognozirovaniya elektropotrebleniya
predpriyatiy s uchetom pogodnykh faktorov [Methodology for providing hourly forecasting of power consumption
of enterprises taking into account weather factors], Vestnik MEI [Bulletin of MPEI], 2007, No. 2,
pp.45-47.
14. Lemeshko B.Yu., Lemeshko S.B., Postovalov S.N., Chimitova E.V. Statisticheskiy analiz dannykh,
modelirovanie i issledovanie veroyatnostnykh zakonomernostey. Komp'yuternyy podkhod:
monografiya [Statistical data analysis, modeling and study of probabilistic patterns. Computer
approach: monograph]. Novosibirsk: Izd-vo NGTU, 2011, 888 p.
15. Spiridonova O.I. Struktura rynka elektroenergii: rynok forvardnykh kontraktov i stimuly k molchalivomu
sgovoru [The structure of the electricity market: the market for forward contracts and incentives for tacit collusion],
Sovremennaya konkurentsiya [Modern competition], 2010, No. 5, pp.15-24.
16. Belov K.D. Patent 115098 RF: MPK G06N 5/00. Mnogosloynaya neyronnaya set' [Patent 115098 RF:
MPK G06N 5/00Multilayer neural network]; applicant and patent holder: Belov K.D.
No. 2011139784/08; appl. 09.29.2011; publ. 04/20/2012; Bull. No. 11.
17. Khamitov R.N. Patent 169425 RF: MPK G06Q 10/06, G06N 5/00. Ustroystvo prognozirovaniya
elektropotrebleniya na osnove mnogosloynoy neyronnoy seti [Patent 169425 RF: IPC G06Q 10/06,
G06N 5/00. Device for forecasting power consumption based on a multilayer neural network]; applicant
and patent holder: Federal State Budgetary Educational Institution of Higher Education Omsk
State Technical University. – No. 2016145339; appl. 11/18/2016; publ. 03/17/2016.
18. Kachelaev O.V., Poluyanovich N.K., Dubyago M.N. Patent 222420 RF: MPK G06N 5/00, G06Q
10/06. Ustroystvo monitoringa i prognozirovaniya elektropotrebleniya v elektroenergeticheskikh
sistemakh na osnove neyronnykh struktur [Patent 222420 RF: IPC G06N 5/00, G06Q 10/06. Device
for monitoring and forecasting power consumption in electric power systems based on neural structures];
patent holder: Federal State Autonomous Educational Institution of Higher Education "Southern
Federal University". No. 2023126166; appl. October 12, 2023; publ. December 25, 2023.
19. Poluyanovich N.K., Azarov N.V., Dubyago M.N. Neyrokomp'yuternoe upravlenie propusknoy
sposobnost'yu kabel'nykh setey posredstvom ucheta i kontrolya ikh parametrov [Neurocomputer control
of the capacity of cable networks through accounting and control of their parameters], Izvestiya
YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2022, No. 3 (227), pp. 84-100.
20. Poluyanovich N.K., Dubyago M.N. Upravlenie propusknoy sposobnost'yu energoseti v zadachakh
prognozirovaniya elektricheskoy nagruzki [Controlling the capacity of the energy network in problems
of forecasting electrical load], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering
Sciences], 2022, No. 6 (230), pp. 30-43.
21. Poluyanovich N.K., Dubyago M.N. Algoritm obucheniya iskusstvennoy neyronnoy seti faktornogo
prognozirovaniya resursa izolyatsionnykh materialov silovykh kabel'nykh liniy [Algorithm for training an
artificial neural network for factor forecasting of the resource of insulating materials of power cable lines],
Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2021, No. 2, pp. 59-73.
22. Dubyago M.N., Poluyanovich N.K. Sovershenstvovanie metodov diagnostiki i prognozirovaniya
elektroizolyatsionnykh materialov sistem energosnabzheniya: monografiya [Improving diagnostic
methods and forecasting of electrical insulating materials for power supply systems: monograph]. Rostov-
on-Don; Taganrog: Izd-vo YuFU, 2019, 192 p.