energyЭнергетика. Известия высших учебных заведений и энергетических объединений СНГENERGETIKA. Proceedings of CIS higher education institutions and power engineering associations1029-74482414-0341BNTU10.21122/1029-7448-2023-66-1-18-29energy-2230Research ArticleЭЛЕКТРОЭНЕРГЕТИКАELECTRICAL POWER ENGINEERINGОперативное прогнозирование скорости ветра для автономной энергетической установки тяговой железнодорожной подстанцииOperational Forecasting of Wind Speed for an Self-Contained Power Assembly of a Traction SubstationМатренинП. B.MatreninP. V.

Новосибирск; Екатеринбург

Novosibirsk; Ekaterinburg

ХальясмааА. И.KhalyasmaaA. I.

Новосибирск; Екатеринбург

Novosibirsk; Ekaterinburg

РусинаА. Г.RusinaA. G.

Новосибирск

Novosibirsk

ЕрошенкоС. А.EroshenkoS. A.

Новосибирск; Екатеринбург

Novosibirsk; Ekaterinburg

ПопковаН. А.PapkovaN. A.

г. Минск

Minsk

СекацкийД. А.SekatskiD. A.

Адрес для переписки:Секацкий Дмитрий Александрович -Белорусский национальный технический университет, просп. Независимости, 65/2,220013, г. Минск, Республика Беларусь.Тел.: +375 17 292-65-82

Address for correspondence:Sekatski Dzmitry A. _Belаrusian National Technical University,65/2, Nezavisimosty Ave.,220013, Minsk, Republic of Belarus.Tel.: +375 17 292-65-82dsekatski@gmail.com

dsekatski@gmail.comНовосибирский государственный технический университет; Уральский федеральный университет имени первого Президента России Б. Н. ЕльцинаРоссияNovosibirsk State Technical University; Ural Federal University named after the first President of Russia B. N. YeltsinRussian FederationНовосибирский государственный технический университетРоссияNovosibirsk State Technical UniversityRussian FederationБелорусский национальный технический университетБеларусьBelаrusian National Technical UniversityBelarus2023060220236611829Copyright © Матренин П.B., Хальясмаа А.И., Русина А.Г., Ерошенко С.А., Попкова Н.А., Секацкий Д.А., 20232023Матренин П.B., Хальясмаа А.И., Русина А.Г., Ерошенко С.А., Попкова Н.А., Секацкий Д.А.Matrenin P.V., Khalyasmaa A.I., Rusina A.G., Eroshenko S.A., Papkova N.A., Sekatski D.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://energy.bntu.by/jour/article/view/2230

В настоящее время рассматриваются перспективы создания гибридных энергетических установок с использованием возобновляемых источников энергии, в том числе энергии ветра, и систем накопления энергии на базе технологий водородной энергетики. Для управления такой системой накопления энергии необходимо оперативное прогнозирование генерации от возобновляемых источников, в частности ветровых энергетических установок. Их выработка зависит от скорости и направления ветра. В статье представлены результаты решения задачи оперативного прогнозирования скорости ветра для проекта гибридной энергетической установки, направленной на повышение пропускной способности железнодорожного участка между станциями Яя и Ижморская (Кемеровская область Российской Федерации). Проанализированы почасовые данные скоростей и направлений ветра за 15 лет, построена нейросетевая модель и предложена компактная архитектура многослойного перцептрона для краткосрочного прогнозирования скорости и направления ветра на 1 и 6 ч вперед. Разработанная модель позволяет минимизировать риски переобучения и потери точности прогнозирования из-за изменения условий работы модели со временем. Особенность данной статьи заключается в исследовании устойчивости модели, обученной на данных многолетних наблюдений, к долгосрочным изменениям, а также анализе возможностей повышения точности прогнозирования за счет регулярного дообучения модели на вновь поступающих данных. Установлен характер влияния размера обучающей выборки и самоадаптации модели на точность прогнозирования и устойчивость ее работы на горизонте в несколько лет. Показано, что для обеспечения высокой точности и устойчивости нейросетевой модели прогнозирования скорости ветра необходимы данные многолетних метеорологических наблюдений.

Currently, the prospects of creating hybrid power assemblies using renewable energy sources, including wind energy, and energy storage systems based on hydrogen energy technologies are being considered. To control such an energy storage system, it is necessary to perform operational renewable sources generation forecasting, particularly forecasting of wind power assemblies. Their production depends on the speed and direction of the wind. The article presents the results of solving the problem of operational forecasting of wind speed for a hybrid power assembly project aimed at increasing the capacity of the railway section between Yaya and Izhmorskaya stations (Kemerovo region of the Russian Federation). Hourly data of wind speeds and directions for 15 years have been analyzed, a neural network model has been built, and a compact architecture of a multilayer perceptron has been proposed for short-term forecasting of wind speed and direction for 1 and 6 hours ahead. The model that has been developed allows minimizing the risks of overfitting and loss of forecasting accuracy due to changes in the operating conditions of the model over time. A specific feature of this work is the stability investigation of the model trained on the data of long-term observations to long-term changes, as well as the analysis of the possibilities of improving the accuracy of forecasting due to regular further training of the model on newly available data. The nature of the influence of the size of the training sample and the self-adaptation of the model on the accuracy of forecasting and the stability of its work on the horizon of several years has been established. It is shown that in order to ensure high accuracy and stability of the neural network model of wind speed forecasting, long-term meteorological observations data are required.

прогнозирование скорости ветраветроэнергетикасистема электрификации железных дорогнейронные сетиwind speed forecastingwind powerrailway electrification systemneural networksReferencesPower Electronic Transformer-Based Railway Traction Systems: Challenges and Opportunities / J. Feng [et al.] // IEEE Journal of Emerging and Selected Topics in Power Electronics. 2017. Vol. 5, Iss. 3. P. 1237–1253. https://doi.org/10.1109/JESTPE.2017.2685464.Feng J., Chu W. Q., Zhang Z., Zhu Z. Q. (2017) Power Electronic Transformer-Based Railway Traction Systems: Challenges and Opportunities. IEEE Journal of Emerging and Selected Topics in Power Electronics, 5 (3), 1237–1253. https://doi.org/10.1109/JESTPE.2017.2685464.Mitrofanov, S. V. Analysis of the Impact of Autonomous Hybrid Power Plants on the Railways Capacity / S. V. Mitrofanov, D. V. Armeev, E. A. Domahin // XV International ScientificTechnical Conference on Actual Problems Of Electronic Instrument Engineering (APEIE). 2021. P. 161–165. https://doi.org/10.1109/APEIE52976.2021.9647596.Mitrofanov S. V., Armeev D. V., Domahin E. A. (2021) Analysis of the Impact of Autonomous Hybrid Power Plants on the Railways Capacity. XV International Scientific-Technical Conference on Actual Problems of Electronic Instrument Engineering (APEIE), 161–165, https://doi.org/10.1109/APEIE52976.2021.9647596.Energetic Simulation of DC Railway Micro-Grid Interconnecting with PV Solar Panels, EV Charger Infrastructures and Electrical Railway Network / J. Pouget [et al.] // IEEE Vehicle Power and Propulsion Conference (VPPC). 2020. P. 1–7. https://doi.org/10.1109/VPPC49601.2020.9330829.Pouget J., Guo B., Bossoney L., Coppex J., Roggo D., Ellert C. (2020) Energetic Simulation of DC Railway Micro-Grid Interconnecting with PV Solar Panels, EV Charger Infrastructures and Electrical Railway Network. IEEE Vehicle Power and Propulsion Conference (VPPC), 1–7. https://doi.org/10.1109/VPPC49601.2020.9330829.Energy Management of a Smart Railway Station Considering Regenerative Braking and Stochastic Behaviour of ESS and PV Generation / İ. Şengör [et al.] // IEEE Transactions on Sustainable Energy. 2018. Vol. 9, Iss. 3. P. 1041–1050. https://doi.org/10.1109/TSTE.2017.2759105.Şengör İ., Kılıçkıran H. C., Akdemir H., Kekezoglu B., Erdinç O., Catalão J. P. S. (2018) Energy Management of a Smart Railway Station Considering Regenerative Braking and Stochastic Behaviour of ESS and PV Generation. IEEE Transactions on Sustainable Energy, 9 (3), 1041–1050. https://doi.org/10.1109/TSTE.2017.2759105.The Potential of Photovoltaics to Power the Railway System in China / L. Ji [et al.] // Energies. 2020. Vol. 13, Iss. 15. P. 3844. https://doi.org/10.3390/en13153844.Ji L., Yu Z., Ma J., Jia L., Ning F. (2020) The Potential of Photovoltaics to Power the Railway System in China. Energies, 13 (15), 3844. https://doi.org/10.3390/en13153844.Mitrofanov, S. V. Stationary Hybrid Renewable Energy Systems for Railway Electrification: A Review / S. V. Mitrofanov, N. G. Kiryanova, A. M. Gorlova // Energies. 2021. Vol. 14, Iss. 18. P. 5946. https://doi.org/10.3390/en14185946.Mitrofanov S. V., Kiryanova N. G., Gorlova A. M. (2021) Stationary Hybrid Renewable Energy Systems for Railway Electrification: A Review. Energies, 14 (18), 5946. https://doi. org/10.3390/en14185946.Aguado, J. A. Optimal Operation of Electric Railways With Renewable Energy and Electric Storage Systems / J. A. Aguado, A. J. Sanchez Racero, S. de la Torre // IEEE Transactions on Smart Grid. 2018. Vol. 9, Iss. 2. P. 993–1001. https://doi.org/10.1109/TSG.2016.2574200.Aguado J. A., Sánchez Racero A. J., Torre de la S. (2018) Optimal Operation of Electric Railways with Renewable Energy and Electric Storage Systems. IEEE Transactions on Smart Grid, 9 (2), 993–1001. https://doi.org/10.1109/TSG.2016.2574200.Evaluation of the Influence of Electrified Railway on Wind Farm / F. Ding [et al.] // IEEE Transportation Electrification Conference and Expo, Asia-Pacific (ITEC Asia-Pacific). 2017. P. 1–6. https://doi.org/10.1109/ITEC-AP.2017.8080804.Ding F., Zhang D., He J., Liu H., Li Y. (2017) Evaluation of the Influence of Electrified Railway on Wind Farm. 2017 IEEE Transportation Electrification Conference and Expo, Asia-Pacific (ITEC Asia-Pacific), 1–6. https://doi.org/10.1109/ITEC-AP.2017.8080804.Гринчик, Н. Н. Oб измерении электрического сопротивления жидких электролитов аккумуляторных батарей / Н. Н. Гринчик, К. В. Добрего, М. А. Чумаченко // Энергетика. Изв. высш. учеб. заведений и энерг. объединений СНГ. 2018. Т. 61, № 6. С. 494–507. https://doi.org/10.21122/1029-7448-2018-61-6-494-507.Grinchik N. N., Dobrego K. V., Chumachenko M. A. (2018) On the Measurement of Electric Resistance of Liquid Electrolytes of Accumulator Battery. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 61 (6), 494–507. https://doi.org/10.21122/1029-7448-2018-61-6-494-507 (in Russian).Добрего, К. B. Моделирование аккумуляторных батарей и их сборок с учетом деградации параметров / К. B. Добрего, Ю. В. Бладыко // Энергетика. Изв. высш. учеб. заведений и энерг. объединений СНГ. 2021. Т. 64, № 1. С. 27–39. https://doi.org/10.21122/1029-7448-2021-64-1-27-39.Dobrego K. V., Bladyko Y. V. (2021) Modeling of Batteries and their Assemblies Taking Into Account the Degradation of Parameters. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 64 (1), 27–39. https://doi.org/ 10.21122/1029-7448-2021-64-1-27-39 (in Russian).Стратегия научно-технологического развития холдинга «Российские железные дороги» на период до 2025 года и на перспективу до 2030 года (Белая книга) [Электронный ресурс] // Инновационный дайджест РЖД. М., 2018. Режим доступа: https://zszd.rzd.ru/api/media/resources/c/17/121/18071?action=download. Дата доступа: 21.03.2022.Strategy for Scientific and Technological Development of Russian Railways Holding for the Period until 2025 and for the Perspective until 2030: White Book. Moscow, 2018. Innovative Digest of RR. Available at: https://zszd.rzd.ru/api/media/resources/c/17/121/18071?action= download (аccessed 21 March 2022) (in Russian).Zhou, Q. Hybrid Forecasting System Based on an Optimal Model Selection Strategy for Different Wind Speed Forecasting Problems / Q. Zhou, C. Wang, G. Zhang // Applied Energy. 2019. Vol. 250. С. 1559–1580. https://doi.org/10.1016/j.apenergy.2019.05.016.Zhou Q., Wang C., Zhang G. (2019) Hybrid Forecasting System Based on an Optimal Model Selection Strategy for Different Wind Speed Forecasting Problems. Applied Energy, 250, 1559–1580. https://doi.org/10.1016/j.apenergy.2019.05.016.Матренин, П. В. Устойчивое краткосрочное прогнозирование скорости ветра с помощью адаптивных компактных нейронных сетей / П. В. Матренин, В. З. Манусов, Е. А. Игумнова // Problemele Energeticii Regionale. 2020. Nо 3. P. 69–80. https://doi.org/10.5281/zenodo.4018960.Matrenin P. V., Manusov V. Z., Igumnova E. A. (2020) Robust Short-Term Wind Speed Forecasting Using Adaptive Shallow Neural Networks. Problemele Energeticii Regionale, 3 (47), 69–80. https://doi.org/10.5281/zenodo.4018960 (in Russian).Current Methods and Advances in Forecasting of Wind Power Generation / A. M. Foley [et al.] // Renewable Energy. 2012. Vol. 37, Iss. 1. P. 1–8. https://doi.org/10.1016/j.renene.2011.05.033.Foley A. M., Leahy P. G., Marvuglia A., McKeogh E. J. (2012) Current Methods and Advances in Forecasting of Wind Power Generation. Renewable Energy, 37 (1), 1–8. https://doi.org/10.1016/j.renene.2011.05.033.Zhang, L. Wind Speed Forecasting Using a Two-Stage Forecasting System with an Error Correcting and Nonlinear Ensemble Strategy / L. Zhang, Y. Dong, J. Wang // IEEE Access. 2019. Vol. 7. P. 176000–176023. https://doi.org/10.1109/ACCESS.2019.2957174.Zhang L., Dong Y., Wang J. (2019) Wind Speed Forecasting Using a Two-Stage Forecasting System with an Error Correcting and Nonlinear Ensemble Strategy. IEEE Access, 7, 176000–176023. https://doi.org/10.1109/ACCESS.2019.2957174.Оптимизация топологии сети с ВИЭ-генерацией на основе модифицированного адаптированного генетического алгоритма / А. М. Брамм [и др.] // Энергетика. Изв. высш. учеб. заведений и энерг. объединений СНГ. 2022. Т. 65, № 4. С. 341–354. https://doi.org/10.21122/1029-7448-2022-65-4-341-354.Bramm A. M., Khalyasmaa A. I., Eroshenko S. A., Matrenin P. V., Papkova N. A., Sekatski D. A. (2022) Topology Optimization of the Network with Renewable Energy Sources Generation Based on a Modified Adapted Genetic Algorithm. Enеrgеtika. Izvestiya Vysshikh Uchebnykh Zavedenii i Energeticheskikh Ob’edinenii SNG = Energetika. Proceedings of CIS Higher Education Institutions and Power Engineering Associations, 65 (4), 341–354. https://doi.org/10.21122/1029-7448-2022-65-4-341-354 (in Russian).Meteoblue, Weather Close to You [Electronic Resource]. Mode of access: https://www.meteoblue.com/en/weather. Date of access: 21.03.2022.Meteoblue, Weather Close to You. Available at https://www.meteoblue.com/en/weather (accessed 1 March 2022).Adaptive Ensemble Models for Medium-Term Forecasting of Water Inflow When Planning Electricity Generation under Climate Change / P. Matrenin [et al.] // Energy Reports. 2022. Vol. 8. P. 439–447. https://doi.org/10.1016/j.egyr.2021.11.112.Matrenin P., Safaraliev M., Dmitriev S., Kokin S., Eshchanov B., Rusina A. (2022) Adaptive Ensemble Models for Medium-Term Forecasting of Water Inflow When Planning Electricity Generation under Climate Change. Energy Reports, 8, Supl. 1, 439–447. https://doi.org/ 10.1016/j.egyr.2021.11.112.Brownlee, J. A Gentle Introduction to the Rectified Linear Unit (ReLU) [Electronic Resource] / J. Brownlee // Machine Learning Mastery. 2019. Mode of access: https://machinelearningmastery.com/rectified-linear-activation-function-for-deep-learning-neural-networks/. Date of access: 08.04.2021.Brownlee J. (2019) A Gentle Introduction to the Rectified Linear Unit (ReLU). Machine Learning Mastery. Available at: https://machinelearningmastery.com/rectified-linear-activa tion-function-for-deep-learning-neural-networks (accessed 8 April 2021).Liu, Danqing. A Practical Guide to ReLU [Electronic Resource] / Danqing Liu // Medium. 2017. Mode of access: https://medium.com/@danqing/a-practical-guide-to-relu-b83ca804f1f7. Date of access: 08.04.2021.Danqing Liu (2017) A Practical Guide to ReLU. Medium. Available at: https://medium.com/@danqing/a-practical-guide-to-relu-b83ca804f1f7 (accessed 8 April 2021).Amini, M. H. ARIMA-Based Decoupled Time Series Forecasting of Electric Vehicle Charging Demand for Stochastic Power System Operation / M. H. Amini, A. Kargarian, O. Karabasoglu // Electric Power Systems Research. 2016. Vol. 140. P. 378–390. https://doi.org/10.1016/j.epsr.2016.06.003.Amini M. H., Kargarian A., Karabasoglu O. (2016) ARIMA-Based Decoupled Time Series Forecasting of Electric Vehicle Charging Demand for Stochastic Power System Operation. Electric Power Systems Research, 140, 378–390. https://doi.org/10.1016/j.epsr.2016.06.003.

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