Повышение качества подбора энергосберегающих мероприятий зданий при использовании искусственных нейронных сетей

Статья посвящена повышению энергосбережения и энергоэффективности учреждений бюджетной сферы за счет автоматизации процесса подбора энергосберегающих мероприятий. В качестве технологии подбора мероприятий в работе предложен классификатор, построенный на базе искусственной нейронной сети. Набор информационных признаков дополнен категориальными данными зданий учреждений. Актуальность работы обоснована необходимостью разработки решений, направленных на внедрение мер по повышению энергосбережения и энергоэффективности в бюджетной сфере. Описаны структура и принцип работы модуля автоматического подбора мероприятий по энергосбережению в составе системы управления энергетическими ресурсами (СУЭР). В работе произведены исследования качества подбора энергосберегающих мероприятий с наличием и отсутствием категориальных признаков. Произведен анализ выделенных категориальных признаков, а также сравнительный анализ методов их кодирования. Предложена методика оценки точности работы классификатора в контексте решаемой задачи. Путем перебора комбинаций методов преобразования количественных и категориальных данных проведен ряд экспериментов с целью определения значимости категориальных признаков в целом, а также определения наиболее результативного сочетания методов их кодирования. Произведен сравнительный анализ полученных результатов с определением наиболее успешной модели, для которой была произведена дополнительная оценка качества работы на базе метрик точности, отклика и средневзвешенной F-меры. Сделаны выводы о целесообразности дополнения исходного набора категориальными данными для улучшения показателей работы разработанной системы.

1. Nekrasov S. A. (2023) Stimulating Electricity Consumption in Outsider Regions is a Necessary Condition for the Structural Stability of Russia. Energetika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 66 (2), 186–200 (accessed 13 November 2024). https://doi.org/10.21122/1029-7448-2023-66-2-186-200 (in Russian).

2. Total energy consumption. Enerdata. Available at: https://energystats.enerdata.net/total-energy/world-consumption-statistics.html. (accessed 15 May 2024).

3. Electrical Balance and Electrical Energy Consumption in the Russian Federation From 2005 to 2022. Federal State Statistics Service. Available at: https://rosstat.gov.ru/storage/mediabank/elbalans_2022.xlsx. (accessed 15 May 2024) (in Russian).

4. Senshinova E. V., Zhuravlev A. E. (2021) Growth in Energy Consumption as One of the Challenges of the 21st Century. Novaya nauka v novom mire: filosofskoe, sotsial’no-ekonomicheskoe, kul’turologicheskoe osmyslenie: Sbornik statei VIII Mezhdunarodnoi nauchno-prakticheskoi konferentsii, Petrozavodsk, 27 maya 2021 goda [New science in the new world: philosophical, socio-economic, culturological understanding: Collection of articles of the VIII International scientific and practical conference, Petrozavodsk, May 27, 2021]. Petrozavodsk, 78–82 (in Russian).

5. Poletaev I. Yu., Androshina I. S. (2023) Formation of the Goals and Objectives of the New State Program for Energy Conservation and Energy Efficiency Improvement of the Russian Economy. Herald of Russian Academy of Natural Sciences = Vestnik Rossiiskoi akademii estestvennykh nauk, 23 (2), 120–124 (in Russian). https://doi.org/10.52531/1682-1696-2023-23-2-120-124.

6. Antonov A. N., Ryzhov G. A. (2010) Actual Issues of Increasing Efficiency and Investment Support for Energy Saving Programs at the Level of Municipalities in Russia. Sovremennye tendentsii v ekonomike i upravlenii: novyi vzglyad. Sbornik dokladov IV Mezhdunarodnoi nauchno-prakticheskoi konferentsii. Ch. 1 [Modern trends in economics and management: a fresh approach. Proceedings of the IV International Scientific and Practical Conference. P. 1]. Novosibirsk, 59–66 (in Russian).

7. Ratner S. V. (2013) Issues of Practical Implementation of State Economic Policy in the Field of Energy Efficiency. Economic analysis: theory and practice, (29), 21–28 (in Russian).

8. On Energy Saving and Improving Energy Efficiency, and on Amendments to Certain Legislative Acts of the Russian Federation: Federal Law, 23.11.2009, No. 261, as amended in 13.06.2023. Available at: https://normativ.kontur.ru/document?moduleId=1&documentId=500643 (in Russian).

9. Nevokshenov A. Yu., Udovik A. V., Yurkovskaya G. I. (2015) Factors Influencing the Implementation of Energy Efficiency Programs and Energy Efficiency of Industrial Enterprises. Sovremennye problemy ekonomicheskogo i sotsial'nogo razvitiya: mezhvuzovskii sbornik nauchnykh trudov. Vyp. 11 [Modern problems of economic and social development. Interuniversity collection of scientific papers. Iss. 11]. Krasnoyarsk, 32–34 (in Russian).

10. Lukishina L. V., Anisimov T. Yu., Mustafina O. N. (2017) Features of the Development of Energy Saving and Energy Efficiency Programs in the Context of Innovative Development of the Russian economy. Innovatsionnoe razvitie rossiiskoi ekonomiki: materialy X Mezhdunarodnoi nauchno-prakticheskoi konferentsii. 25–27 oktyabrya 2017 g. T. 2 [Innovative development of the Russian economy: Proceedings of the X International scientific and practical conference: in five volumes, Moscow, October 25–27, 2017. Vol. 2]. Moscow, Plekhanov Russian University of Economics, 272–275 (in Russian).

11. Lebedeva N. A., Poletaeva L. P., Svezhintsev P. S. (2018) Adaptive Approach to the Formation of an Energy Saving Program. Intellekt. Innovatsii. Investitsii = Intellect. Innovations. Investments, (10), 24–27 (in Russian).

12. Li C. Z., Zhang L., Liang X., Xiao B., Tam V. W. Y., Lai X., Chen Z. (2022) Advances in the Research of Building Energy Saving. Energy and Buildings, 254, 111556. https://doi.org/10.1016/j.enbuild.2021.111556.

13. Mohsen M. S., Akash B. A. (2001) Some Prospects of Energy Savings in Buildings. Energy Conversion and Management, 42 (11), 1307–1315. https://doi.org/10.1016/s0196-8904(00)00140-0.

14. Popescu D., Bienert S., Schützenhofer C., Boazu R. (2012) Impact of Energy Efficiency Measures on the Economic Value of Buildings. Applied Energy, 89 (1), 454–463. https://doi.org/10.1016/j.apenergy.2011.08.015.

15. Song K., Ahn Y., Ahn J., Kwon N. (2019) Development of an Energy Saving Strategy Model for Retrofitting Existing Buildings: A Korean Case Study. Energies, 12 (9), 1626. https://doi.org/10.3390/en12091626.

16. Farkhutdinov R. R. (2017) Energy Saving Tools and their Application within the Framework of Regional Development Programs. Alleya nauki = Alley of Science, 3 (13), 555–559 (in Russian).

17. Koshlich Yu., Belousov A., Trubaev P., Grebenik A., Bukhanov D. (2020) Control Systems of Regional Energy Resources as a Digital Platform for Smart Cities. da Silva Bartolo P. J., da Silva F. M., Jaradat S., Bartolo H. (eds.). Industry 4.0 – Shaping The Future of The Digital World. London, CRC Press, 309–313. https://doi.org/10.1201/9780367823085-54.

18. Kuzmin A. M., Vysokovskaya E. A. (2019) The span Diagram is One of the Tools for Statistical Data Processing. Metody menedzhmenta kachestva = Methods of Quality Management, (11), 39 (in Russian).

19. Starovoytov V. V., Golub Yu. I. (2021) Data Normalization in Machine Learning. Informatics, 18 (3), 83–96 (in Russian). https://doi.org/10.37661/1816-0301-2021-18-3-83-96.

20. Ascione F., Bianco N., De Stasio C., Mauro G. M., Vanoli G. P. (2017) Artificial Neural Networks to Predict Energy Performance and Retrofit Scenarios for any Member of a Building category: A Novel Approach. Energy, 118, 999–1017. https://doi.org/10.1016/j.energy.2016.10.126.

21. Mokrousova E. S., Romodin A. V. (2010) The issue of Creation of a Mathematical Model of an Artificial Neural Network Within the Framework of the Development of an Automated System for Managing Energy Saving Programs. Vestnik Permskogo gosudarstvennogo tekhnicheskogo universiteta. Elektrotekhnika, informatsionnye tekhnologii, sistemy upravleniya = Bulletin of the Perm State Technical University. Electrical engineering, information technology, control systems, (4), 72–76 (in Russian).

22. Sednin A. V., Zherelo A. V. (2022) An Approach to Data Processing for the Smart District Heating System. Energetika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 65 (3), 240–249 (accessed 13 November 2024).https://doi.org/10.21122/1029-7448-2022-65-3-240-249 (in Russian).

23. Zhang H., Feng H., Hewage K., Arashpour M. (2022) Artificial Neural Network for Predicting Building Energy Performance: A Surrogate Energy Retrofits Decision Support Framework. Buildings, 12 (6), 829. https://doi.org/10.3390/buildings12060829.

24. Albon C. (2018) Machine Learning with Python Cookbook. O'Reilly Media. 364.

25. Grus J. (2019) Data Science from Scratch First Principles with Python. O'Reilly Media. 403.

26. Categorical Variable Encoding. Kaggle. Available at:https://www.kaggle.com/code/harishvutukuri/categorical-variable-encoding (accessed 13 Juny 2024).

27. Processing of Categorical Features. Habr. Available at: https://habr.com/ru/articles/666234/ (accessed 13 Juny 2024) (in Russian).

28. Potdar K., Taher S., Chinmay D. (2017) A Comparative Study of Categorical Variable Encoding Techniques for Neural Network Classifiers. International Journal of Computer Applications, 175 (4), 7–9. https://doi.org/10.5120/ijca2017915495.

29. Novikova D. V. (2022) Comparative Analysis of the Effectiveness of Methods for Coding categorical Variables in the Problem of Predicting the Safety of Therapy for Multiple Sclerosis. Zametki po informatike i matematike: Sbornik nauchnykh statei. Vyp. 14 [Notes on computer science and mathematics: Collection of scientific articles. Vol. 14]. Yaroslavl, Yaroslavl State University named after P.G. Demidov, 61–69 (in Russian).

30. Barkov D. V., Senotova S. A. (2021) Encoding of Categorical Features in Neural Networks. Scientific Papers Collection of the Angarsk State Technical University, 2021 (1), 3–8. https://doi.org/10.36629/2686-7788-2021-1-1-3-8 (in Russian).

31. Dong G., Liu H. (2018) Feature Engineering for Machine Learning and Data Analytics. CRC Press. 400. https://doi.org/10.1201/9781315181080.

32. Zheng A., Casari A. (2018) Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists. O'Reilly Media. 215.

33. Ilyukovich-Strakovskaya A. M. (2015) Methods of Handle Categorial Features in Classification Problem. Informatsionno-telekommunikatsionnye tekhnologii i matematicheskoe modelirovanie vysokotekhnologichnykh sistem: materialy Vserossiiskoi konferentsii s mezhdunarodnym uchastiem. Moskva, 20–24 aprelya 2015 g. [Information and telecommunication technologies and mathematical modeling of high-tech systems: Proceedings of the All-Russian conference with international participation, Moscow, April 20–24, 2015]. Moscow, Peoples’ Friendship University of Russia, 137–139 (in Russian).

34. Ezukwoke K. I. (2023) Data Transformation for Machine Learning. Available at: https://www.academia.edu/40436475/Data_Transformation_for_Machine_Learning.

35. Keras API. Available at: https://keras.io/ (accessed 22 Juny 2024).

36. Scikit-learn. Available at: https://scikit-learn.org (accessed 22 June 2024).

37. Sokolova M., Japkowicz N., Szpakowicz S. (2006) Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation. Sattar A., Kang Bh. (eds). AI 2006: Advances in Artificial Intelligence. Lecture Notes in Computer Science, vol. 4304. Springer, Berlin, Heidelberg, 1015–1021. https://doi.org/10.1007/11941439_114.