Development of Software Tools for Calculating and Forecasting the Integral Index of the Heat Supply System of Typical Buildings Based on Neural Network Methods

  • Павел [Pavel] Романович [R.] Варшавский [Varshavskii]
  • Сергей [Sergey] Вадимович [V.] Гужов [Guzhov]
  • Анатолий [Anatoliy] Андреевич [A.] Сесин [Sesin]
  • Матвей [Matvey] Сергеевич [S.] Башлыков [Bashlykov]
Keywords: building heat consumption mathematical model, database, integral index, demand forecasting, energy efficiency, reliability, artificial neural network

Abstract

The article addresses an urgent problem of developing methods and software tools for calculating and predicting the integral index of building energy systems based on their energy efficiency and reliability, which has been solved only partially in view of the complexity of collecting all data about the building in the currently available complex mathematical models. It is proposed to make a shift to calculating the energy system integral index using artificial neural networks. This will make it possible to significantly simplify the procedure of formulating the system of initial equations by using statistical data on the object under study.

The architecture of the developed prototype software system is presented together with a database scheme, which describes the correlation of available building data, based on which the integral index components (energy efficiency and reliability indicators) are calculated.

For solving the problem of predicting the demand for building energy systems’ energy resources on the basis of data obtained from open-access sources, it is proposed to apply a method on the basis of the specially organized artificial neural network described in this article.

The applicability of the study results to the of "green construction" objects and office buildings of business centers in Moscow is shown.

Information about authors

Павел [Pavel] Романович [R.] Варшавский [Varshavskii]

Ph.D. (Techn.), Head of Applied Mathematics and Artificial Intelligence Dept., NRU MPEI, e-mail: VarshavskyPR@mpei.ru

Сергей [Sergey] Вадимович [V.] Гужов [Guzhov]

Ph.D. (Techn.), Assistant Professor of Heat-and-mass Exchange Processes and Installations Dept., NRU MPEI, e-mail: GuzhovSV@mpei.ru

Анатолий [Anatoliy] Андреевич [A.] Сесин [Sesin]

Assistant of Applied Mathematics and Artificial Intelligence Dept., NRU MPEI, e-mail: SesinAA@mpei.ru

Матвей [Matvey] Сергеевич [S.] Башлыков [Bashlykov]

Student of Applied Mathematics and Artificial Intelligence Dept., NRU MPEI, e-mail: BashlykovMatS@mpei.ru

References

1. Грицай А.А. Сравнительный анализ методик оценки экономического развития предприятия // Роль государственной статистики в развитии современного общества: Материалы Междунар. науч.-практ. конф. 2018. Т. 2. С. 136—142.
2. Ведерников А.С., Ярыгина Е.А., Гофман А.В. Выбор метода для задач краткосрочного прогнозирования электропотребления собственных нужд ТЭЦ // Вестник Ивановского гос. энергетического ун-та. 2018. № 6. С. 32—38.
3. Башлыков А.А., Еремеев А.П. Методы и программные средства конструирования интеллектуальных систем поддержки принятия решений для объектов энергетики // Вестник МЭИ. 2018. № 1. С. 72—85.
4. Варшавский П.Р., Еремеев А.П. Моделирование рассуждений на основе прецедентов в интеллектуальных системах поддержки принятия решений // Искусственный интеллект и принятие решений. 2009. № 2. С. 45—57.
5. Firsova I.A. e. a. Energy Consumption Forecasting for Power Supply Companies // Intern. J. Energy Economics and Policy. 2019. V. 9(1). Pp. 1—6.
6. Popov V., Fedosenko M., Tkachenko V., Yatsenko D. Forecasting Consumption of Electrical Energy Using Time Series Comprised of Uncertain Data // Proc. IEEE VI Intern. Conf. Energy Smart Systems. 2019. Pp. 201—204.
7. Lemke F. Probabilistic Energy Forecasting Based on Self-organizing Inductive Modeling // Advances in Intelligent Systems and Computing. 2019. V. 871. Pp. 405—420.
8. Wang J. e. a. Data Center Energy Consumption Models and Energy Efficient Algorithms // Jisuanji Yanjiu yu Fazhan. 2019. V. 56(8). Pp. 1587—1603.
9. Jiang P., Dong J., Huang H. Forecasting China's Renewable Energy Terminal Power Consumption Based on Empirical Mode Decomposition and an Improved Extreme Learning Machine Optimized by a Bacterial Foraging Algorithm // Energies. 2019. V. 12(7). P. 1331.
10. Runge J., Zmeureanu R. Forecasting Energy Use in Buildings Using Artificial Neural Networks: a Review // Energies. 2019. V. 12(17). P. 3254.
11. Андреева Т.Ю., Софроницкий А.П., Гужов С.В. Индекс энергетической эффективности офисных зданий в г. Москва // Advances of Science 2021: Материалы VII Междунар. науч.-практ. конф. Москва, 2021. С. 19—21.
12. Софроницкий А.П., Андреева Т.Ю., Гужов С.В. Индекс надёжности офисных зданий в г. Москва // Там же. С. 28—30.
13. Google for Developers [Электрон. ресурс] https://developers.google.com/machine-learning/data-prep/transform/normalization (дата обращения 16.08.2023).
14. 6.3. Preprocessing Data — Scikit-learn 1.2.2 Documentation [Электрон. ресурс] https://scikit-learn.org/stable/modules/preprocessing.html (дата обращения 16.08.2023).
---
Для цитирования: Варшавский П.Р., Гужов С.В., Сесин А.А., Башлыков М.С. Разработка программных средств для расчёта и прогнозирования интегрального индекса системы теплоснабжения типовых зданий на основе нейросетевых методов // Вестник МЭИ. 2024. № 1. С. 138—146. DOI: 10.24160/1993-6982-2024-1-138-146
---
Работа выполнена в рамках проекта «Разработка нейросетевого программного обеспечения по прогнозированию спроса на тепловую энергию объектами массового строительства города Москвы» при поддержке гранта НИУ «МЭИ» на реализацию программы научных исследований «Приоритет 2030: Технологии будущего» в 2022 — 2024 гг
#
1. Gritsay A.A. Sravnitel'nyy Analiz Metodik Otsenki Ekonomicheskogo Razvitiya Predpriyatiya. Rol' Gosudarstvennoy Statistiki V Razvitii Sovremennogo Obshchestva: Materialy Mezhdunar. Nauch.-Prakt. Konf. 2018;2:136—142. (in Russian).
2. Vedernikov A.S., Yarygina E.A., Gofman A.V. Vybor Metoda dlya Zadach Kratkosrochnogo Prognozirovaniya Elektropotrebleniya Sobstvennykh Nuzhd TETS. Vestnik Ivanovskogo Gos. Energeticheskogo Un-ta. 2018;6:32—38. (in Russian).
3. Bashlykov A.A., Eremeev A.P. Metody i Programmnye Sredstva Konstruirovaniya Intellektual'nykh Sistem Podderzhki Prinyatiya Resheniy Dlya Ob'ektov Energetiki. Vestnik MEI. 2018;1:72—85. (in Russian).
4. Varshavskiy P.R., Eremeev A.P. Modelirovanie Rassuzhdeniy na Osnove Pretsedentov v Intellektual'nykh Sistemakh Podderzhki Prinyatiya Resheniy. Iskusstvennyy Intellekt i Prinyatie Resheniy. 2009;2:45—57. (in Russian).
5. Firsova I.A. e. a. Energy Consumption Forecasting for Power Supply Companies. Intern. J. Energy Economics and Policy. 2019;9(1):1—6.
6. Popov V., Fedosenko M., Tkachenko V., Yatsenko D. Forecasting Consumption of Electrical Energy Using Time Series Comprised of Uncertain Data. Proc. IEEE VI Intern. Conf. Energy Smart Systems. 2019:201—204.
7. Lemke F. Probabilistic Energy Forecasting Based on Self-organizing Inductive Modeling // Advances in Intelligent Systems and Computing. 2019;871:405—420.
8. Wang J. e. a. Data Center Energy Consumption Models and Energy Efficient Algorithms. Jisuanji Yanjiu yu Fazhan. 2019;56(8):1587—1603.
9. Jiang P., Dong J., Huang H. Forecasting China's Renewable Energy Terminal Power Consumption Based on Empirical Mode Decomposition and an Improved Extreme Learning Machine Optimized by a Bacterial Foraging Algorithm. Energies. 2019;12(7):1331.
10. Runge J., Zmeureanu R. Forecasting Energy Use in Buildings Using Artificial Neural Networks: a Review. Energies. 2019;12(17):3254.
11. Andreeva T.YU., Sofronitskiy A.P., Guzhov S.V. Indeks Energeticheskoy Effektivnosti Ofisnykh Zdaniy v g. Moskva. Advances of Science 2021: Materialy VII Mezhdunar. Nauch.-prakt. Konf. Moskva, 2021:19—21. (in Russian).
12. Sofronitskiy A.P., Andreeva T.Yu., Guzhov S.V. Indeks Nadezhnosti Ofisnykh Zdaniy v g. Moskva. Tam zhe:28—30. (in Russian).
13. Google for Developers [Elektron. Resurs] https://developers.google.com/machine-learning/data-prep/transform/normalization (Data Obrashcheniya 16.08.2023).
14. 6.3. Preprocessing Data — Scikit-learn 1.2.2 Documentation [Elektron. Resurs] https://scikit-learn.org/stable/modules/preprocessing.html (Data Obrashcheniya 16.08.2023)
---
For citation: Varshavskii P.R., Guzhov S.V., Sesin A.A., Bashlykov M.S. Development of Software Tools for Calculating and Forecasting the Integral Index of the Heat Supply System of Typical Buildings Based on Neural Network Methods. Bulletin of MPEI. 2024;1:138—146. (in Russian). DOI: 10.24160/1993-6982-2024-1-138-146
---
The work is executed within the Framework of the Project «Development of Neural Network Software for Forecasting Demand for Thermal Energy by Mass Construction Facilities in Moscow» with the Support of a Grant from the NRU «MPEI» for the Implementation of the Research Program «Priority 2030: Technologies of the Future» in 2022 — 2024
Published
2023-10-18
Section
Computer Science and Information Processes (Technical Sciences) (2.3.8)