novtexmechМехатроника, автоматизация, управлениеMekhatronika, Avtomatizatsiya, Upravlenie1684-64272619-1253Commercial Publisher «New Technologies»10.17587/mau.24.307-316novtexmech-1392Research ArticleАВТОМАТИЗАЦИЯ И УПРАВЛЕНИЕ ТЕХНОЛОГИЧЕСКИМИ ПРОЦЕССАМИAUTOMATION AND CONTROL TECHNOLOGICAL PROCESSESИнтеллектуальное прогнозирование потребления электроэнергии при управлении энергетическими предприятиями на основе нейросетевых технологийIntelligent Forecasting of Electricity Consumption in Managing Energy Enterprises in Order to Carry out Energy-Saving MeasuresПальчевскийЕ. В.PalchevskyE. V.

преподаватель

г. Москва

Moscow, 109456

teelxp@inbox.ruАнтоновВ. В.AntonovV. V.

д-р техн. наук, проф.

г. Уфа

Ufa, 450008

antonov.v@bashkortostan.ruКроминаЛ. А.KrominaL. E.

канд. техн. наук, доц.

г. Уфа

Ufa, 450008

luyda-kr@yandex.ruРодионоваЛ. Е.RodionovaL. E.

канд. техн. наук, доц.

г. Уфа

Ufa, 450008

lurik@mail.ruФахруллинаА. Р.FakhrullinaA. R.

канд. техн. наук, доц.

г. Уфа

Ufa, 450008

almirafax@mail.ruФинансовый университет при Правительстве Российской ФедерацииРоссияFinancial University under the Government of the Russian FederationRussian FederationУфимский университет науки и технологийРоссияUfa University of Science and TechnologyRussian Federation202314062023246307316Copyright © Commercial Publisher «New Technologies», 20232023Commercial Publisher «New Technologies»Commercial Publisher «New Technologies»https://mech.novtex.ru/jour/about/submissions#copyrightNoticehttps://mech.novtex.ru/jour/article/view/1392

В концепции "Цифровая трансформация 2030", определяющей национальные цели и стратегические задачи развития Российской Федерации на период до 2030 года, указаны специализированные цели и задачи, являющиеся важным посылом для внедрения интеллектуальных информационных технологий управления в сферу электроэнергетики. Основными вызовами для перехода к цифровой трансформации являются увеличение темпов роста тарифов для конечного потребителя, нарастающий износ сетевой инфраструктуры, наличие избыточного сетевого строительства и повышение требований к качеству энергопотребления.

Определяющим фактором возможности разработки эффективной энергетической политики является прогнозирование потребления электроэнергии с использованием методов искусственного интеллекта. Одним из методов реализации вышесказанного является разработка искусственной нейронной сети (ИНС) для получения заблаговременного прогноза количества требуемой (потребляемой) электроэнергии. Полученные прогнозные значения открывают возможность не только выстроить грамотную энергетическую политику путем повышения энергоэффективности энергетической компании, но и проводить специализированные энергосберегающие мероприятия в целях оптимизации бюджета организации.

Решение данной проблемы представлено в виде искусственной нейронной сети второго поколения. Основными преимуществами данной ИНС являются универсальность, скоростное и точное обучение, а также отсутствие необходимости в большом количестве исходных данных для качественного прогноза. За основу самой ИНС берутся классический нейрон и метод обратного распространения ошибки с их дальнейшей модификацией. В метод обратного распространения ошибки добавлены коэффициенты скорости обучения и чувствительности, а в нейрон внедрен коэффициент реагирования на аномалии во временных рядах. Это позволило существенно улучшить скорость обучения искусственной нейронной сети и повысить точность прогнозных результатов.

Представленные в настоящем исследовании результаты могут быть взяты в качестве ориентира для энергетических компаний при принятии решений в рамках энергетической политики, в том числе и при проведении энергосберегающих мероприятий, что будет особенно полезным в текущих экономических реалиях.

The concept of "Digital Transformation 2030", which defines the national goals and strategic objectives of the development of the Russian Federation for the period up to 2030, specifies specialized goals and objectives that are an important message for the introduction of intelligent information management technologies in the electric power industry. The main challenges for the transition to digital transformation are the increase in the rate of growth of tariffs for the end consumer, the increasing wear and tear of the network infrastructure, the presence of excessive network construction and the increase in requirements for the quality of energy consumption. The determining factor in the possibility of developing an effective energy policy is the forecasting of electricity consumption using artificial intelligence methods. One of the methods for implementing the above is the development of an artificial neural network (ANN) to obtain an early forecast of the amount of required (consumed) electricity. The obtained predictive values open up the possibility not only to build a competent energy policy by increasing the energy efficiency of an energy company, but also to carry out specialized energy-saving measures in order to optimize the organization’s budget. The solution to this problem is presented in the form of an artificial neural network (ANN) of the second generation. The main advantages of this ANN are its versatility, fast and accurate learning, as well as the absence of the need for a large amount of initial da-ta for a qualitative forecast. The ANN itself is based on the classical neuron and the error back-propagation method with their further modification. The coefficients of learning rate and sensitivity have been added to the error backpropagation method, and the coefficient of response to anomalies in the time series has been introduced into the neuron. This made it possible to significantly improve the learning rate of the artificial neural network and improve the accuracy of predictive results. The results presented by this study can be taken as a guideline for energy companies when making decisions within the framework of energy policy, including when carrying out energy saving measures, which will be especially useful in the current economic realities.

нейронные сетиискусственный интеллектинтеллектуальное прогнозирование потребления электроэнергииинтеллектуальный анализ данныхэнергоэффективностьуправление в энергетикеneural networksartificial intelligenceintelligent forecasting of electricity consumptiondata miningenergy efficiencymanagement in the energy sectorИсследование выполнено при финансовой поддержке Минобрнауки РФ в рамках базовой части госзадания вузам № FEUE–2023–0007.The research was supported by the Ministry of Science and Higher Education of the Russian Federation as part of the State Assignment № FEUE—2023—0007.ReferencesLouis-Gabriel M., Louis G. Forecasting of short-term lighting and plug load electricity consumption in single residential units: Development and assessment of data-driven models for different horizons, Applied Energy, 2022, no. 307, pp. 118229.Louis-Gabriel M., Louis G. Forecasting of short-term lighting and plug load electricity consumption in single residential units: Development and assessment of data-driven models for different horizons, Applied Energy, 2022, no. 307, pp. 118229.Hadjout D. et al. Electricity consumption forecasting based on ensemble deep learning with application to the Algerian market, Energy, 2022, no. 243, pp. 123060.Hadjout D. et al. Electricity consumption forecasting based on ensemble deep learning with application to the Algerian market, Energy, 2022, no. 243, pp. 123060.Garant, available at: https://base.garant.ru/70643464/ (date of access to the page: 13.08.22).Garant, available at: https://base.garant.ru/70643464/ (date of access to the page: 13.08.22).Jian D. et. al. A hybrid deep learning framework for predicting daily natural gas consumption, Energy, 2022, 257, pp. 124689.Jian D. et. al. A hybrid deep learning framework for predicting daily natural gas consumption, Energy, 2022, 257, pp. 124689.Tasarruf B. et. al. Short term electricity load forecasting using hybrid prophet-LSTM model optimized by BPNN, Energy Reports, 2022, no 8, pp. 1678—1686.Tasarruf B. et. al. Short term electricity load forecasting using hybrid prophet-LSTM model optimized by BPNN, Energy Reports, 2022, no 8, pp. 1678—1686.Hongcheng L. et. al. Data-driven hybrid petri-net based energy consumption behaviour modelling for digital twin of energy-efficient manufacturing system, Energy, 2022, 239, pp. 122178.Hongcheng L. et. al. Data-driven hybrid petri-net based energy consumption behaviour modelling for digital twin of energy-efficient manufacturing system, Energy, 2022, 239, pp. 122178.Chengyu Z., Tianyi Z., Kuishan L. Quantitative correlation models between electricity consumption and behaviors about lighting, sockets and others for electricity consumption prediction in typical campus buildings, Energy and Buildings, 2021, no 253, pp. 111510.Chengyu Z., Tianyi Z., Kuishan L. Quantitative correlation models between electricity consumption and behaviors about lighting, sockets and others for electricity consumption prediction in typical campus buildings, Energy and Buildings, 2021, no 253, pp. 111510.Meng Z. et. al. A novel flexible grey multivariable model and its application in forecasting energy consumption in China, Energy, 2022, no 239-E, pp. 122441.Meng Z. et. al. A novel flexible grey multivariable model and its application in forecasting energy consumption in China, Energy, 2022, no 239-E, pp. 122441.Fazil K. et al. A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption, Energy, 2020, no 197, pp. 117200.Fazil K. et al. A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption, Energy, 2020, no 197, pp. 117200.Ying S. et al. Prediction method of electricity stealing behavior based on multi-dimensional features and BP neural network, Energy Reports, 2022, no. 8—4, pp. 523—531.Ying S. et al. Prediction method of electricity stealing behavior based on multi-dimensional features and BP neural network, Energy Reports, 2022, no. 8—4, pp. 523—531.Vyalkova S. A., Nadtoka I. I. Forecasting daily graphs active energy consumption of a megapolis taking into account forecast data of daylight illumination. Izvestiya vysshih uchebnyh zavedenij. Elektromekhanika, vol. 63, no. 5, pp. 67—71 (In Russian)Vyalkova S. A., Nadtoka I. I. Forecasting daily graphs active energy consumption of a megapolis taking into account forecast data of daylight illumination. Izvestiya vysshih uchebnyh zavedenij. Elektromekhanika, vol. 63, no. 5, pp. 67—71 (In Russian)Safaraliev M. H. et al. Adaptive ensemble models for medium-term forecasting of power generation by hydropower plants in isolated power systems taking into account temperature changes, Electrotechnical Systems and Complexes, no. 1(54), pp. 38—45.Safaraliev M. H. et al. Adaptive ensemble models for medium-term forecasting of power generation by hydropower plants in isolated power systems taking into account temperature changes, Electrotechnical Systems and Complexes, no. 1(54), pp. 38—45.McCulloch W. S., Pitts W. A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 1943, no. 5, pp. 115—133.McCulloch W. S., Pitts W. A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 1943, no. 5, pp. 115—133.Palchevsky E. V., Antonov V. V. Decision support system based on application of the second generation neural network, Programmnaya Ingeneria, 2022, no. 13-6, pp. 301—308.Palchevsky E. V., Antonov V. V. Decision support system based on application of the second generation neural network, Programmnaya Ingeneria, 2022, no. 13-6, pp. 301—308.Palchevsky E. V., Khristodulo O. I., Pavlov S. V. Threat prediction in complex distributed systems using artificial neural network technology, CEUR Workshop Proceedings, 2020, no. 2763, pp. 289—284.Palchevsky E. V., Khristodulo O. I., Pavlov S. V. Threat prediction in complex distributed systems using artificial neural network technology, CEUR Workshop Proceedings, 2020, no. 2763, pp. 289—284.Mitchell T. Machine Learning, 1997, 432 p.Mitchell T. Machine Learning, 1997, 432 p.Fukushima K. Visual Feature Extraction by a Multilayered Network of Analog Threshold Elements, IEEE Transactions on Systems Science and Cybernetics, 1969, no. 5—4, pp. 322—333.Fukushima K. Visual Feature Extraction by a Multilayered Network of Analog Threshold Elements, IEEE Transactions on Systems Science and Cybernetics, 1969, no. 5—4, pp. 322—333.Palchevsky E. V. et al. Intelligent data analysis for forecasting threats in complex distributed systems, CEUR Workshop Proceedings, 2020, no. 2744, pp. 285—296.Palchevsky E. V. et al. Intelligent data analysis for forecasting threats in complex distributed systems, CEUR Workshop Proceedings, 2020, no. 2744, pp. 285—296.

The authors declare that there are no conflicts of interest present.