Среднесрочное прогнозирование естественного притока к створу ГЭС и корректировка номинальной мощности с помощью применения технологий водородной энергетики

В статье содержится обоснование важности и необходимости прогнозирования естественного притока к створу ГЭС, а также изложение основных принципов, затрудняющих управление режимами ГЭС без моделей прогнозирования. Отдельное внимание уделяется описанию используемых методов прогнозирования, оценки их точности, достоинств и недостатков. Создание модели и опробование алгоритмов прогнозирования естественного притока к створу ГЭС реализовано методами машинного обучения в Python с использованием библиотеки scikit-learn. В качестве объекта исследования выбрана Новосибирская ГЭС.

В ходе сбора и анализа данных была создана выборка из метеорологических сведений за 3287 дней со значениями температуры воздуха, давления, осадков, влажности и естественного притока к створу ГЭС. Прогнозирование притока к створу ГЭС реализовано на моделях линейной регрессии, полиноминальной регрессии второй степени, ближайших соседей, деревьев решений и случайного леса решений.

Полученные результаты оценки критериев точности MAPE, RMSE, R2 и MSE для каждой из рассматриваемых моделей прогнозов естественного притока к створу ГЭС показали, что реализация наиболее точного среднесрочного прогноза притока к створу ГЭС была достигнута моделью на основе случайного леса деревьев решений.

1. . Electricity load forecasting: A systematic review / I.K. Nti, M. Teimeh, Nyarko-Boateng, A.F. Adekoya // Journal of Electrical Systems and Information Technology. – 2020. – Vol. 7, iss. 1. – P. 1-19.

2. . M. Zarghami, J. Aghaei, M. Alipour and M. R. Salehizadeh, «Flexibility Forecasting of Cellular Electric Energy Systems Using Machine Learning Techniques», 2022 18th International Conference on the European Energy Market (EEM), Ljubljana, Slovenia, 2022, pp. 1-5.

3. . R. A. Iringan Iii, A. M. S. Janer and L. A. R. Tria. «A Machine-learning Based Energy Management System for Microgrids with Distributed Energy Resources and Storage», 2022 25th International Conference on Electrical Machines and Systems (ICEMS), Chiang Mai, Thailand, 2022, pp. 1-6.

4. . N. Shabbir, R. AhmadiAhangar, L. Kütt, M. N. Iqbal and A. Rosin. «Forecasting Short Term Wind Energy Generation using Machine Learning», 2019 IEEE 60th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON), Riga, Latvia, 2019, pp. 1-4.

5. . Pavel Matrenin, Murodbek Safaraliev, Stepan Dmitriev, Sergey Kokin, Anvari Ghulomzoda, Sergey Mitrofanov, Medium-term load forecasting in isolated power systems based on ensemble machine learning models, Energy Reports, Volume 8, Supplement 1, 2022, Pages 612-618.

6. . P. Matrenin, A. Khalyasmaa, S. Eroshenko and A. Rusina. «Application of Swarm Intelligence Algorithms to Optimize the Power Consumption Model», 2021 IEEE Second International Conference on Control, Measurement and Instrumentation (CMI), Kolkata, India, 2021, pp. 72-75.

7. . A. Bramm and A. Khalyasmaa. «Forecasting Accuracy Improvement of Solar Power Plant’s Generation». Proc. of 2021 XVIII International Scientific Technical Conference Alternating Current Electric Drives (ACED), Ekaterinburg, Russia, 2021, doi: 10.1109/ACED50605.2021.9462283

8. . Chen, B. -J. Load forecasting using support vector machines: a study on EUNITE competition 2001 / B. -J. Chen, M.-W. Chang, Ch.-J. Lin // IEEE Transactions on Power Systems. – 2004. – Vol. 19, iss. 4. – P. 1821-1830.

9. . G. Mitchell, S. Bahadoorsingh, N. Ramsamooj and C. Sharma. «A comparison of artificial neural networks and support vector machines for short-term load forecasting using various load types». 2017 IEEE Manchester PowerTech, Manchester, UK, 2017, pp. 1-4.

10. . Y. Cai, Q. Xie, C. Wang and F. Lü. «Shortterm load forecasting for city holidays based on genetic support vector machines». 2011 International Conference on Electrical and Control Engineering, Yichang, China, 2011, pp. 3144-3147.

11. . S. Li, K. Ma, Z. Jin and Y. Zhu. «A new flood forecasting model based on SVM and boosting learning algorithms». 2016 IEEE Congress on Evolutionary Computation (CEC), Vancouver, BC, Canada, 2016, pp. 1343-1348.

12. . M. Sarhani, A. E. Afia Electric load forecasting using hybrid machine learning approach incorporating feature selection. Proceedings of the International Conference on Big Data Cloud and Applications Tetuan, Morocco, May 25-26, 2015.

13. . Sergeev, N. N. Enhancing Efficiency of Ensemble Machine Learning Models for Short-Term Load Forecasting through Feature Selection / N. N. Sergeev, P. V. Matrenin // 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials (EDM): proc., Altai, 30 June 2022 – 04 July 2022. – Altai: IEEE, 2022. – P. 368-371.

14. . Zhu, J. Using markov chains for link prediction in adaptive web sites / J. Zhu, J. Hong, J. G. Hughes // Int. Conference on Soft Issues in the Design, Development, and Operation of Computing Systems: proc., Berlin, Heidelberg, 10 April 2002. – Berlin, Heidelberg: Springer, 2002. – P. 60-73.

15. . D. Apostolopoulou, Z. De Grève and M. McCulloch. «Robust Optimization for Hydroelectric System Operation Under Uncertainty», in IEEE Transactions on Power Systems, vol. 33, no. 3, pp. 3337-3348.

16. . Papadopoulos, Sokratis & Karakatsanis, Ioannis. (2015). Short-term electricity load forecasting using time series and ensemble learning methods. 2015 IEEE Power and Energy Conference at Illinois, PECI 2015. 10.1109/PECI.2015.7064913.

17. . M. Matos, J. Almeida, P. Gonçalves, F. Baldo, F. J. Braz and P. Bartolomeu. «A Machine Learning Based Energy Management System for Renewable Energy Communities». 2023 IEEE 3rd International Conference on Industrial Electronics for Sustainable Energy Systems (IESES), Shanghai, China, 2023, pp. 1-6.

18. . Y. Fan and W. Lei. «Wind Speed Prediction Based on Gradient Boosting Decision Tree». 2022 International Conference on Big Data, Information and Computer Network (BDICN), Sanya, China, 2022, pp. 93-97.

19. . N. F. Cheganova, P. V. Matrenin and S. V. Mitrofanov. «Medium-Term Forecast of Water Inflow to the Sayano-Shushenskaya Hydroelectric Power Plant Reservoir by Autoregressive Machine Learning Models». 2023 IEEE XVI International Scientific and Technical Conference Actual Problems of Electronic Instrument Engineering (APEIE), Novosibirsk, Russian Federation, 2023, pp. 470-473.

20. . Cover, T. Nearest neighbor pattern classification / T. Cover, P. Hart // IEEE Trans. Inf. Theory. – 1967. – Vol. 13. – P. 21-27.

21. . S. S. Pattanaik, A. K. Sahoo and R. Panda. «A Comparative Analysis of KNN and Light GBM Algorithms for Wind Energy Forecasting». 2023 1st International Conference on Circuits, Power and Intelligent Systems (CCPIS), Bhubaneswar, India, 2023, pp. 1-4.

22. . I. Jahan, F. Mohamed, V. Blazek, L. Prokop, S. Misak and V. Snasel. «Power Quality Parameters Forecasting Based on SOM Maps with KNN Algorithm and Decision Tree». 2023 23rd International Scientific Conference on Electric Power Engineering (EPE), Brno, Czech Republic, 2023, pp. 1-6.

23. . Potential of Artificial Neural Network to Power System Operation / M. J. Damborg, M. A El-Sharkawi, M. E. Aggoune, R. J. Marks II // IEEE International Symposium on Circuits and Systems: proc., New Orleans, LA, 01-03 May 1990. – New Orleans, LA: IEEE, 1990. – P. 2933-2937.

24. . Xifeng Guo, Qiannan Zhao, Di Zheng, Yi Ning, Ye Gao, A short-term load forecasting model of multiscale CNN-LSTM hybrid neural network considering the real-time electricity price, Energy Reports, Volume 6, Supplement 9, 2020, Pages 1046-1053, ISSN 2352-4847, https://doi.org/10.1016/j.egyr.2020.11.078.

25. . O. Y. Maryasin and A. Plohotnyuk. «DayAhead Power Forecasting of Renewable Energy Sources Using Neural Networks and Machine Learning». 2023 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), Sochi, Russian Federation, 2023, pp. 130-135.

26. . K. Okoli and Y. A. Bekeneva. «Accurate Neural Prophecy for Short-Term Load Forecasting of Optimal Renewable Energy». 2023 V International Conference on Control in Technical Systems (CTS), Saint Petersburg, Russian Federation, 2023, pp. 196-198.

27. . Weimin B., Wei S., Simin Q. Flow updating in real-time flood forecasting based on runoff correction by a dynamic system response curve J. Hydrol. Eng., 19 (4) (2013), pp. 747-756.

28. . Simin Q., Weimin B., Peng S., Zhongbo Y., Peng J. Water-stage forecasting in a multitributary tidal river using a bidirectional Muskingum method J. Hydrol. Eng., 14 (12) (2009), pp. 1299-1308.

29. . Vrugt J. A., H. V. Gupta, W. Bouten, S. Sorooshian. A shuffled complex evolution metropolis algorithm for estimating posterior distribution of watershed model parameters Calibration Watershed Models (2003), pp. 105-112.

30. . Jialan Sun, Xiaohui Lei, Weihong Liao, Yunzhong Jiang and Hao Wang. «Development of a flood forecasting system and its application to upper reaches of Zhangweihe River Basin». 2012 International Symposium on Geomatics for Integrated Water Resource Management, Lanzhou, 2012, pp. 1-4.

31. . K. Allaev, T. Makhmudov, and D. Losev, «Short-term forecasting of electricity generation by HPP’s of power system of Uzbekistan». E3S Web of Conf., vol. 365 01015, 2023, doi:10.1051/e3sconf/202336501015.

32. . D. Losev. «The long-term forecasting of specific fuel consumption by the power system of Uzbekistan». E3S Web of Conf., vol. 216, 01101, 2020, doi:10.1051/e3sconf/202021601101.

33. . J. Wang, P. Shi, P. Jiang, J. Hu, S. Qu, X. Chen, Y. Chen, Y. Dai, Z. Xiao. Application of BP neural network algorithm in traditional hydrological model for flood forecasting Water, 9 (1) (2017), p. 48.

34. . Ekanayake, P., Wickramasinghe, L., Jayasinghe, J. M. J. W., & Rathnayake, U. (2021). Regression-Based Prediction of Power Generation at Samanalawewa Hydropower Plant in Sri Lanka Using Machine Learning. Mathematical Problems in Engineering, 2021, 1-12. https://doi.org/10.1155/2021/4913824.

35. . Bernardes, J., Jr.; Santos, M.; Abreu, T.; Prado, L., Jr.; Miranda, D.; Julio, R.; Viana, P.; Fonseca, M.; Bortoni, E.; Bastos, G.S. Hydropower Operation Optimization Using Machine Learning: A Systematic Review. AI 2022, 3, 78-99. https://doi.org/10.3390/ai3010006.

36. . Bilgili, M., Keiyinci, S., Ekinci, F. One-day ahead forecasting of energy production from run-of-river hydroelectric power plants with a deep learning approach. Scientia Iranica, 2022; 29(4): 1838-1852. doi: 10.24200/sci.2022.58636.5825.

37. . Pavel Matrenin, Murodbek Safaraliev, Stepan Dmitriev, Sergey Kokin, Bahtiyor Eshchanov, Anastasia Rusina. Adaptive ensemble models for medium-term forecasting of water inflow when planning electricity generation under climate change, Energy Reports, Volume 8, Supplement 1, 2022, Pages 439-447, ISSN 2352-4847, https://doi.org/10.1016/j.egyr.2021.11.112.

38. . S. V. Mitrofanov, P. V. Matrenin and U. A. Sekretarev. «Analysis of the Natural Inflow Short-term Forecasting Models Efficiency to the HPP Site for the Day-ahead Based on Regression Methods and Machine Learning Methods» 2023 IEEE 24th International Conference of Young Professionals in Electron Devices and Materials (EDM), Novosibirsk, Russian Federation, 2023, pp. 1130-1134.

39. . A. Sauhats, R. Petrichenko, K. Baltputnis, Z. Broka and R. Varfolomejeva. «A multi-objective stochastic approach to hydroelectric power generation scheduling». 2016 Power Systems Computation Conference (PSCC), Genoa, Italy, 2016, pp. 1-7.

40. . Bilgili, M., Keiyinci, S., Ekinci, F. One-day ahead forecasting of energy production from run-of-river hydroelectric power plants with a deep learning approach. Scientia Iranica, 2022; 29(4): 1838-1852. doi: 10.24200/sci.2022.58636.5825.

41. . Farmer, J. D., Sidorowich, J. J.: Predicting chaotic time series. Physical Review Letters 8(59), 845-848 (1987). [42]. Bontempi, Gianluca & Ben Taieb, Souhaib & Le Borgne, Yann-Aël. (2013). Machine Learning Strategies for Time Series Forecasting. 10.1007/978-3-642-36318-4_3.

42. . Soren Bisgaard, Murat Kulahci Time Series Analysis and Forecasting by Example / Series: Wiley Series in Probability and Statistics Publisher: Wiley, Year: 2011, ISBN: 0470540648,9780470540640,97811180569 43,9781118056950.

43. . Kalita, J. (2022). Machine Learning: Theory and Practice (1st ed.). Chapman and Hall/CRC. https://doi.org/10.1201/9781003002611.

44. . NASA POWER [electronic source]. – Available: https://power.larc.nasa.gov/data-access-viewer/.

45. . Уровни водохранилищ ГЭС [electronic source]. – Available: https://rushydro.ru/informer/?-date=2017-01-04