Short-Term Forecasting of Power Consumption of Power Supply Companies Based on the Integration of Technologies of Analytical, Simulation and Expert Systems

Purpose of research is to improve software support and identify regularities in the processes of short-term forecasting of power consumption of power supply companies based on complementary integration of data mining models, system dynamics and expert systems.

Methods. The principles of constructing predictive models of power consumption are given. A system analysis has been carried out and an ontological model of the subject area has been built, taking into account the technological and market environment. The classification of forecasting methods has been considered. The features of the information base for short-term forecasting, including data on actual power consumption and weather data, have been described. The requirements for software for making forecasts have been formulated. A block diagram of the system for forecasting power consumption of the market for the day ahead is built based on the complementary integration of data analysis and modeling software.

Results. Scenarios for data processing in Loginom have been developed using the Arimax and Neural Network (Regression) processors to build forecasts based on actual power consumption and taking into account meteorological factors. A system dynamics simulation model that allows exploring the influence of meteorological factors (temperature, pressure, precipitation) on power consumption has been developed in Anylogic. Using Wi!Mi mivar constructor of expert systems, the task has been parametrized; indicators, relationships, rules have been set; a logical conclusion of the solution has been obtained.

Conclusion. A block diagram of a system for forecasting the market's power consumption for the day ahead has been built. It is based on the analysis of retrospective information on actual power consumption and meteorological factors using data mining methods, system dynamics and expert systems applying Russian Loginom, Anylogic and Wi!Mi software tools.

1. Optovyj rynok jelektricheskoj jenergii i moshhnosti [Wholesale market of electric energy and capacity]. Associacija «NP Sovet rynka» [Association "NP Market Counci"]. Available at: www.np-sr.ru/ru/market/wholesale/index.htm (accessed date: 14.04.2022).

2. Po krivoj – k balansu. Kak skladyvaetsja cena jelektrojenergii [By curve - to the balance sheet. How is the price of electricity]. OOO «Sibirskaja generirujushhaja kompanija» [Sibirskaya Generating Company LLC]. Available at: www.sibgenco.online/news/element/on-a-curve-to-balance-what-is-the-price-of-electricity-/ (accessed date:14.04.2022).

3. Solovyova I.A., Dziuba A.P. Prognozirovanie jelektropotreblenija s uchetom faktorov tehnologicheskoj i rynochnoj sredy [Forecasting of power consumption taking into accountthe factors of the technological and market environment]. Nauchnyj dialog = Scientific Dialogue. 2013, no 7 (19), pp. 97-113.

4. Smirnova E.O., Filatov A.Yu. Prognozirovanie rynka jelektrojenergii "na sutki vpered": primer vtoroj cenovoj zony [Forecasting the electricity market "for the day ahead": an example of the second price zone]. Vestnik Voronezhskogo gosudarstvennogo universiteta. Serija: Jekonomika i upravlenie = Bulletin of Voronezh State University. Series: Economics and Governance, 2018, no. 4, pp. 149-159.

5. Mokhov V.G., Demyanenko T.S. Prognozirovanie potreblenija jelektricheskoj jenergii na optovom rynke jelektrojenergii i moshhnosti [Forecasting of electric energy consumption in the wholesale electricity and capacity market]. Vestnik Juzhno-Ural'skogo gosudarstvennogo universiteta. Serija: Jekonomika i menedzhment = Bulletin of South Ural State University. Series: Economics and Management, 2014, vol. 8, no. 2, pp. 86-92.

6. Voronov I.V., Politov E.A., Efremenko V.M. Ispol'zovanie nejronnoj seti dlja kratkosrochnogo prognozirovanija jelektropotreblenija promyshlennogo predprijatija [Using a neural network for short-term forecasting of the power consumption of an industrial enterprise]. Vestnik KuzGTU = Bulletin of KuzGTU, 2006, no. 6, pp. 71-73.

7. Serebryakov N.A. Vybor optimal'noj arhitektury i konfiguracii nejroseti v zadachah kratkosrochnogo prognozirovanija jelektropotreblenija garantirujushhego postavshhika jelektrojenergii [Choosing the optimal architecture and configuration of the neural network in the tasks of short-term forecasting of the power consumption of the guaranteeing electricity supplier]. Vesti vysshih uchebnyh zavedenij Chernozem'ja = News of Higher Educational Institutions of the Chernozem Region, 2021, no. 2 (64), pp. 26-42.

8. Karpenko S.M., Karpenko N.V., Bezginov G.Yu. Prognozirovanie jelektropotreblenija na gornopromyshlennyh predprijatijah s ispol'zovaniem statisticheskih metodov [Forecasting of power consumption at mining enterprises using statistical methods]. Gornaja promyshlennost' = Mining Industry, 2022, no. 1, pp. 82-88.

9. Filippova T.A., Rusina A.G., Dronova Yu.V., Zimin R.V., Kalyuzhny R.S. Ispol'zovanie statisticheskih modelej pri kratkosrochnom prognozirovanii jelektropotreblenija i grafikov nagruzki JeJeS [Use of statistical models in short-term forecasting of power consumption and EES load plots]. Jelektricheskie stancii = Electrical Stations, 2008, no. 5, pp. 32-36.

10. Makoklyuev B.I., Polizharov A.S., Lomeiko A.A., Mishina V.V. Prognozirovanie jelektropotreblenija jenergosbytovyh kompani [Forecasting the power consumption of energy sales companies]. Jenergojekspert = Energoexpert, 2018, no. 1(65), pp. 34-38.

11. Bershadsky I.A., Dzhura S.G., Chursinova A.A. Ispol'zovanie iskusstvennogo intellekta dlja prognozirovanija jelektropotreblenija jenergosbytovoj kompanii [The use of artificial intelligence to predict the power consumption of an energy sales company]. Nauchnyjvestnik Novosibirskogo gosudarstvennogo tehnicheskogo universiteta = Scientific Bulletin of Novosibirsk State Technical University, 2020, no. 4(80), pp. 7-16.

12. Tyunkov D.A., Sapilova A.A., Gritsa.i A.S., Alekseenko D.A., Khamitov R.N. Metody kratkosrochnogo prognozirovanija vyrabotki jelektricheskoj jenergii solnechnymi jelektrostancijami i ih klassifikacija [Methods of short-term forecasting of electric power generation by solar power plants and their classification]. Jelektrotehnicheskie sistemy i kompleksy = Electrical Systems and Complexes, 2020, no. 3(48), pp. 4-10.

13. Abdurakhmanov A.M., Volodin M.V., Zybin E.Yu., Ryabchenko V.N. Metody prognozirovanija jelektropotreblenija v raspredelitel'nyh setjah (obzor) [Methods for predicting power consumption in distribution networks (overview )]. Jelektrotehnika: setevoj jelektronnyj nauchnyj zhurnal = Electrical Engineering: Network Electronic Scientific Journal, 2016, vol. 3, no. 1, pp. 3-23.

14. Halyasmaa A.I., Matrenin P.V., Eroshenko S.A. Analiz oshibok primenenija algoritmov mashinnogo obuchenija v zadachah jelektrojenergetiki [Analysis of errors in the application of machine learning algorithms in the problems of the electric power industry]. Jelektrojenergija. Peredacha i raspredelenie = Electricity. Transmission and Distribution. 2021, no. 3(66), pp. 46-53.

15. Bubnovskaya T.V., Demonova T.I. Sovershenstvovanie sistemy informacionnogo obespechenija processov upravlenija v jenergosbytovoj kompanii [Improving the information support system for management processes in the energy sales company]. Azimut nauchnyh issledovanij: jekonomika i upravlenie = Azimut of Scientific Research: Economics and Management. 2018, vol. 7, no. 4(25), pp. 89-92.

16. Kretov D.A., Ruzanov R.V. Prognozirovanie jelektropotreblenija jenergosbytovoj kompanii s ispol'zovaniem iskusstvennoj nejronnoj seti [Forecasting the power consumption of an energy sales company using an artificial neural network]. Inzhenernyj vestnik Dona = Engineering Bulletin of the Don, 2015, no 2-1(35), pp. 20.

17. Paklin N.B., Ilyin I.V., Shirokova S.V. Malokodovye platformy v podgotovke analitikov dannyh [Small-code platforms in the preparation of data analysts]. Fundamental'nye i prikladnye issledovanija v oblasti upravlenija, jekonomiki i torgovli. Sbornik trudov Vserossijskoj nauchno-prakticheskoj i uchebno-metodicheskoj konferencii [Fundamental and applied research in the field of management, economics and trade. Collection of works of the All-Russian scientific-practical and educational-methodological conference]. St. Petersburg, 2021, pp. 218-221.

18. Borshchev A.V., Makhdavi A. Imitacionnye modeli kak virtual'naja sreda dlja obuchenija i testirovanija iskusstvennogo intellekta dlja biznes-prilozhenij [Imitation models as a virtual environment for training and testing artificial intelligence for business applications]. Devjataja vserossijskaja nauchno-prakticheskaja konferencija po imitacionnomu modelirovaniju i ego primeneniju v nauke i promyshlennosti. Trudy konferencii [Ninth AllRussian scientific and practical conference on imitation modeling and its application in science and industry. Proceedings of the conference]. Ekaterinburg, 2019, pp. 20-29.

19. Nazarov K.V., Varlamov O.O. Razrabotka metodiki sozdanija verificiruemyh modelej dlja mivarnyh jekspertnyh system [Development of methodology for creation of verifiable models for mivar expert systems]. T-Comm: Telekommunikacii i transport = T-Comm: Telecommunications and Transport, 2017, vol. 11, no. 4, pp. 64-71.

20. Ganyukov V.Yu., Khanova A.A., Suldina N.V. Intellektual'naya sistema upravleniya cepyami postavok logisticheskogo predpriyatiya na osnove diskretno-sobytijnoj, agentnoj i sistemno- dinamicheskoj imitacionnyh modelej [Intelligent supply chain management system of a logistics enterprise based on discrete-event, agent and system-dynamic simulation models]. Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika i informatika= Bulletin of the Astrakhan State Technical University. Series: Management, Computer Engineering and Informatics, 2012, no. 2, pp. 143-149.