Обзор международного опыта в прогнозировании генерации возобновляемых источников энергии с помощью методов машинного обучения

Цель – проведение аналитического обзора и систематизация современных подходов к прогнозированию генерации электроэнергии на базе возобновляемых источников энергии в мировой практике, а также анализ актуальных проблем и перспективных решений в данном направлении. Классификация методов прогнозирования генерации электроэнергии возобновляемыми источниками выполнена на основе анализа литературных источников, посвященных разработке моделей прогнозирования, которые включают в себя физические модели, использование статистических методов и методов на базе машинного обучения. Проведен анализ использования наиболее распространенных методов (физических, статистических и методов машинного обучения) прогнозирования генерации электроэнергии возобновляемыми источниками, выделены преимущества и недостатки данных методов. Установлено, что в большинстве случаев – в особенности в задачах краткосрочного прогнозирования генерации – методы прогнозирования на базе машинного обучения показывают более высокие результаты по сравнению с физическими и статистическими методами. По результатам анализа актуальных проблем в области систем сбора метеоданных установлено, что основными препятствиями для широкого применения алгоритмов машинного обучения на практике являются неполнота и неопределенность исходных данных, а также высокая вычислительная сложность таких алгоритмов. Показано, что с целью повышения эффективности моделей машинного обучения в задаче прогнозирования генерации возобновляемых источников энергии можно применять различные методы предварительной обработки данных, такие как нормализация, определение аномалий и восстановление пропущенных значений, аугментация и кластеризация, корреляционный анализ. Принято решение о необходимости разработки методов предварительной обработки данных , направленных на оптимизацию и общее повышение эффективности моделей машинного обучения для прогнозирования генерации возобновляемых источников энергии. Ведение исследований в данном направлении при учете всех перечисленных проблем имеет высокую значимость для реализации программ по интеграции возобновляемых источников энергии в электроэнергетическую систему и развития в области безуглеродной энергетики.

1. Илюшин П.В. Интеграция электростанций на основе возобновляемых источников энергии в Единую энергетическую систему России: обзор проблемных вопросов и подходов к их решению // Вестник Московского энергетического института. Вестник МЭИ. 2022. № 4. С. 98–107. https://doi.org/10.24160/1993-6982-2022-4-98-107.

2. Kolosok S., Bilan Yu., Vasylieva T., Wojciechowski A., Morawski M. A scoping review of renewable energy, sustainability and the environment // Energies. 2021. Vol. 14. Iss. 15. P. 4490. https://doi.org/10.3390/en14154490.

3. Qazi A., Hussain F., Rahim N. A., Hardaker G., Alghazzawi D., Shaban K., et al. Towards sustainable energy: a sy stematic review of renewable energy sources, technologies, and public opinions // IEEE Access. 2019. Vol. 7. P. 63837 – 63851. https://doi.org/10.1109/ACCESS.2019.2906402.

4. Sinsel S.R., Riemke R.L., Hoffmann V.H. Challenges and solution technologies for the integration of variable renewable energy sources—a review // Renewable Energy. 2020. Vol. 145. P. 2271–2285. https://doi.org/10.1016/j.renene.2019.06.147.

5. Yang Yuqing, Bremner Stephen, Menictas Chris, Kay Merlinde. Battery energy storage system size determination in renewable energy systems: а review // Renewable and Sustainable Energy Reviews. 2018. Vol. 91. P. 109–125. https://doi.org/10.1016/j.rser.2018.03.047.

6. Wan Can, Zhao Jian, Song Yonghua, Xu Zhao, Lin Jin, Hu Zechun. Photovoltaic and solar po wer forecasting for smart grid energy management // CSEE Journal of Power and Energy Systems. 2015. Vol. 1. Iss. 4. P. 38 –46. https://doi.org/10.17775/CSEEJPES.2015.00046.

7. Santhosh M., Venkaiah C., Kumar D.M.V. Current advances and approaches in wind speed and wind power forecasting for improved renewable energy integration: а review // Engineering Reports. 2020. Vol. 2. Iss. 6. P. e12178. https://doi.org/10.1002/eng2.12178.

8. Azad H.B., Mekhilef S., Ganapathy V.G. Long-term wind speed forecasting and general pattern recognition using neural networks // IEEE Transactions on Sustainable Energy. 2014. Vol. 5. Iss. 2. P. 546–553. https://doi.org/10.1109/TSTE.2014.2300150.

9. Ahmed R., Sreeram V., Mishra Y., Arif M.D. A review and evaluation of the state-of-the-art in PV solar power forecasting: techniques and optimization // Renewable and Sustainable Energy Reviews. 2020. Vol. 124. P. 109792. https://doi.org/10.1016/j.rser.2020.109792.

10. Mehmood F., Ghani M.U., Asim M.N., Shahzadi R., Mehmood A., Mahmood W. MPF-Net: a computational multiregional solar power forecasting framework // Renewable and Sustainable Energy Reviews. 2021. Vol. 151. P. 111559. https://doi.org/10.1016/j.rser.2021.111559.

11. Wang Xiaochen, Guo Peng, Huang Xiaobin. A review of wind power forecasting models // Energy Procedia. 2011. Vol. 12. P. 770–778. https://doi.org/10.1016/j.egypro.2011.10.103.

12. Varanasi J., Tripathi M.M. A comparative study of wind power forecasting techniques – A review article // 3rd International Conference on Computing for Sustainable Global Development (New Delhi, 16–18 March 2016). New Delhi: IEEE, 2016. P. 3649–3655.

13. Sweeney C., Bessa R.J., Browell J., Pinson P. The future of forecasting for renewable energy // Wiley Interdisciplinary Reviews: Energy and Environment. 2020. Vol. 9. Iss. 2. P. e365. https://doi.org/10.1002/wene.365.

14. Aslam S., Herodotou H., Mohsin S.M. Javaid N. Ashraf N., Aslam S. A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids // Renewable and Sustainable Energy Reviews. 2021. Vol. 144. P. 110992. https://doi.org/10.1016/j.rser.2021.110992.

15. Hanifi S., Liu Xiaolei, Lin Zi, Lotfian S. A critical review of wind power forecasting methods–past, present and future // Energies. 2020. Vol. 13. Iss. 15. P. 3764. https://doi.org/10.3390/en13153764.

16. Voyant C., Notton G., Kalogirou S., Nivet M.-L., Paoli C., Motte F., et al. Machine learning methods for solar radiation forecasting: a review // Renewable Energy. 2017. Vol. 105. P. 569–582. https://doi.org/10.1016/j.renene.2016.12.095.

17. Zhou Kaile, Fu Chao, Yang Shanlin. Big data driven smart energy management: from big data to big insights // Renewable and Sustainable Energy Reviews. 2016. Vol. 56. P. 215–225. https://doi.org/10.1016/j.rser.2015.11.050.

18. Yeom Jong-Min, Deo R.C., Adamwoski J.F., Chae Taebyeong, Kim Dong-Su, Han Kyung-Soo, et al. Exploring solar and wind energy resources in North Korea with COMS MI geostationary satellite data coupled with numerical weather prediction reanalysis variables // Renewable and Sustainable Energy Reviews. 2020. Vol. 119. P. 109570. https://doi.org/10.1016/j.rser.2019.109570.

19. Schultz M.G., Betancourt C., Gong B., Kleinert F., Langguth M., Leufen L.H. et al. Can deep learning beat numerical weather prediction? // Philosophical Transactions of the Royal Society A. 2021. Vol. 379. Iss. 2194. P. 20200097. https://doi.org/10.1098/rsta.2020.0097.

20. Andrade J.R., Bessa R.J. Improving renewable energy forecasting with a grid of numerical weather predictions // IEEE Transactions on Sustainable Energy. 2017. Vol. 8. Iss. 4. P. 1571–1580. https://doi.org/10.1109/TSTE.2017.2694340.

21. Aguiar L.M., Pereira B., Lauret P., Díaz F., David M. Combining solar irradiance measurements, satellite-derived data and a numerical weather prediction model to improve intra-day solar forecasting // Renewable Energy. 2016. Vol. 97. P. 599–610. https://doi.org/10.1016/j.renene.2016.06.018.

22. Dutta S., Li Yanling, Venkataraman A., Costa L.M., Jiang Tianxiang, Plana R. et al. Load and renewable en ergy forecasting for a microgrid using persistence technique // Energy Procedia. 2017. Vol. 143. P. 617 –622. https://doi.org/10.1016/j.egypro.2017.12.736.

23. Wang Jingmin, Zhou Qingwei, Zhang Xueting. Wind power forecasting based on time series ARMA model // Earth and Environmental Science: IOP Conference series. 2018. Vol. 199. Iss. 2. P. 022015. https://doi.org/10.1088/17551315/199/2/022015.

24. Singh B., Pozo D. A guide to solar power forecasting using ARMA models // IEEE PES Innovative Smart Grid Technologies Europe ISGT-Europe. 2019. https://doi.org/10.1109/ISGTEurope.2019.8905430.

25. Cadenas E., Rivera W., Campos-Amezcua R., Heard C. Wind speed prediction using a univariate ARIMA model and a multivariate NARX model // Energies. 2016. Vol. 9. Iss. 2. P. 109. https://doi.org/10.3390/en9020109.

26. Grigonytė E., Butkevičiūtė E. Short-term wind speed forecasting using ARIMA model // Energetika. 2016. Vol. 62. Iss. 1-2. Р. 3313. https://doi.org/10.6001/energetika.v62i1-2.3313.

27. Robles-Rodriguez C.E., Dochain D. Decomposed Threshold ARMAX Models for short-to medium-term wind power forecasting // IFAC-PapersOnLine. 2018. Vol. 51. Iss. 13. P. 49–54. https://doi.org/10.1016/j.ifacol.2018.07.253.

28. Li Yanting, Su Yan, Shu Lianjie. An ARMAX model for forecasting the power output of a grid connected photovoltai c system // Renewable Energy. 2014. Vol. 66. P. 78–89. https://doi.org/10.1016/j.renene.2013.11.067.

29. Dev S., AlSkaif T., Hossari M., Godina R., Louwen A., Sark W. Solar irradiance forecasting using triple exponential smoothing // International Conference on Smart Energy Systems and Technologies SEST. 2018. https://doi.org/10.1109/SEST.2018.8495816.

30. Zheng Xidong, Jin Tao. A reliable method of wind power fluctuation smoothing strategy based on multidimensional non‐linear exponential smoothing short‐term forecasting // IET Renewable Power Generation. 2022. Vol. 16. Iss. 16. P. 3573–3586. https://doi.org/10.1049/rpg2.12395.

31. Bulut M., Hakan T., Buaisha M. Comparison of three different learning methods of multilayer Perceptron neural network for wind speed forecasting // Gazi University Journal of Science. 2021. Vol. 34. Iss. 2. P. 439–454. https://doi.org/10.35378/gujs.764533.

32. Wang Zheng, Wang Bo, Liu Chun, Wang Wei-sheng. Improved BP neural network algorithm to wind power forecast // The Journal of Engineering. 2017. Vol. 2017. Iss. 13. P. 940–943. https://doi.org/10.1049/joe.2017.0469.

33. Abuella M., Chowdhury B. Solar power forecasting using artificial neural networks // North American Power Symposium NAPS. 2015. https://doi.org/10.1109/NAPS.2015.7335176.

34. Manusov V., Matrenin P., Nazarov M., Beryozkina S., Safaraliev M., Zicmane I., et al. Short-term prediction of the wind speed based on a learning process control algorithm in isolated power systems // Sustainability. 2023. Vol. 15. Iss. 2. P. 1730. https://doi.org/10.3390/su15021730.

35. Feng Cong, Zhang Jie. SolarNet: a sky image-based deep convolutional neural network for intra-hour solar forecasting // Solar Energy. 2020. Vol. 204. P. 71–78. https://doi.org/10.1016/j.solener.2020.03.083.

36. Zhu Qiaomu, Chen Jinfu, Zhu Lin, Duan Xianzhong, Liu Yilu, et al. Wind speed prediction with spatio–temporal correlation: a deep learning approach // Energies. 2018. Vol. 11. Iss. 4. P. 705. https://doi.org/10.3390/en11040705.

37. Alkhayat G., Mehmood R. A review and taxonomy of wind and solar energy forecasting methods based on deep learning // Energy and AI. 2021. Vol. 4. P. 100060. https://doi.org/10.1016/j.egyai.2021.100060.

38. Al-Sbou Y.A., Alawasa K.M. Nonlinear autoregressive recurrent neural network model for solar radiation prediction // International Journal of Applied Engineering Research. 2017. Vol. 12. Iss. 14. P. 4518–4527.

39. Cali U., Sharma V. Short-term wind power forecasting using long-short term memory based recurrent neural network model and variable selection // International Journal of Smart Grid and Clean Energy. 2019. Vol. 8. Iss. 2. P. 103 –110. http://doi.org/10.12720/sgce.8.2.103-110.

40. Kisvari A., Lin Zi, Liu Xiaolei. Wind power forecasting – a data-driven method along with gated recurrent neural network // Renewable Energy. 2021. Vol. 163. P. 1895–1909. https://doi.org/10.1016/j.renene.2020.10.119.

41. Zendehboudi A., Baseer M.A., Saidur R. Application of support vector machine models for forecasting solar and wind energy resources: a review // Journal of Cleaner Production. 2018. Vol. 199. P. 272–285. https://doi.org/10.1016/j.jclepro.2018.07.164.

42. Li Ling-Ling, Zhao Xue, Tseng Ming-Lang, Tan Raymond R. Short-term wind power forecasting based on support vector machine with improved dragonfly algorithm // Journal of Cleaner Production. 2020. Vol. 242. P. 118447. https://doi.org/10.1016/j.jclepro.2019.118447.

43. Jang Han Seung, Bae Kuk Yeol, Park Hong-Shik, Sung Dan Keun. Solar power prediction based on satellite images and support vector machine // IEEE Transactions on Sustainable Energy. 2016. Vol. 7. Iss. 3. P. 1255 –1263. https://doi.org/10.1109/TSTE.2016.2535466.

44. Zhou Kaile, Fu Chao, Yang Shanlin. Big data driven smart energy management: from big data to big insights // Renewable and Sustainable Energy Reviews. 2016. Vol. 56. P. 215–225. https://doi.org/10.1016/j.rser.2015.11.050.

45. Matrenin P.V., Atabaeva L.S., Sergeev N.N. Limitations and perspectives of short-term renewable energy generation forecasting methods // IEEE International Multi-Conference on Engineering, Computer and Information Sciences SIBIRCON. 2022. https://doi.org/10.1109/SIBIRCON56155.2022.10017051.

46. Al-Dahidi S., Ayadi O., Alrbai M., Adeeb J. Ensemble approach of optimized artificial neural networks for solar photovoltaic power prediction // IEEE Access. 2019. Vol. 7. P. 81741–81758. https://doi.org/10.1109/ACCESS.2019.2923905.

47. Al-Jarrah O.Y., Yoo P.D., Muhaidat S., Karagiannidis G.K., Taha K. Efficient machine learning for big data: a review // Big Data Research. 2015. Vol. 2. Iss. 3. P. 87–93. https://doi.org/10.1016/j.bdr.2015.04.001.

48. Suresh V., Janik P., Rezmer J., Leonowicz Z. Forecasting solar PV output using convolutional neural networks with a sliding window algorithm // Energies. 2020. Vol. 13. Iss. 3. P. 723. https://doi.org/10.3390/en13030723.

49. Ziegler L., Gonzalez E., Rubert T., Smolka U., Melero J.J. Lifetime extension of onshore wind turbines: a review covering Germany, Spain, Denmark, and the UK // Renewable and Sustainable Energy Reviews. 2018. Vol. 82. Part 1. P. 1261–1271. https://doi.org/10.1016/j.rser.2017.09.100.

50. Kim Taeyoung, Ko Woong, Kim Jinho. Analysis and impact evaluation of missing data imputation in day-ahead PV generation forecasting // Applied Sciences. 2019. Vol. 9. Iss. 1. P. 204. https://doi.org/10.3390/app9010204.

51. Yen Chih-Feng, Hsieh He-Yen, Su Kuan-Wu, Yu Min-Chieh, Leu Jenq-Shiou. Solar power prediction via support vector machine and random forest // International Conference Green Energy and Smart Grids: E3S Web of Conferences. 2018. Vol. 69. P. 01004. https://doi.org/10.1051/e3sconf/20186901004.

52. Nie Yuhao, Zamzam A.S., Brandt A. Resampling and data augmentation for short-term PV output prediction based on an imbalanced sky images dataset using convolutional neural networks // Solar Energy. 2021. Vol. 224. P. 341 –354. https://doi.org/10.1016/j.solener.2021.05.095.

53. Wang Zheng, Koprinska I., Rana M. Clustering based methods for solar power forecasting // International Joint Conference on Neural Networks IJCNN (Vancouver, 24–29 July 2016). Vancouver: IEEE, 2016. P. 1487–1494. https://doi.org/10.1109/IJCNN.2016.7727374.

54. Chen Hailang, Chang Xianfa. Photovoltaic power prediction of LSTM model based on Pearson feature selection // Energy Reports. 2021. Vol. 7. P. 1047–1054. https://doi.org/10.1016/j.egyr.2021.09.167.