Machine Learning Application for Renewable Energy Forecasting
Main Article Content
Keywords
Forecasting, Ensemble machine learning, Photovoltaic power plant, Wind farm
Abstract
Renewable energy is a clean source known as green energy. Its benefits are enough established. However, its effective use and increasing its share have become a major challenge for system operators. Due to its direct dependence on environmental and meteorological factors, there are often uncertainties and unexpected consequences for integrated energy system planning. Thus, the prediction of the production of renewable sources is a very relevant issue. This paper considers the application of ensemble machine learning models for renewable energy forecasting. As input data for the machine learning modem, historical data on power generation was used for the 2019–2021 period of renewable energy including meteorological data from the power plants operating in the central power system of Mongolia. The ensemble machine learning model allows us to determine the non-linear and non-stationary dependence of the time series and can be implemented in the task of forecasting the daily generation schedule. The proposed model creates a day-ahead forecast of the hourly generation curve of the photo-voltaic power plants under consideration with a normalized absolute percentage error of 6.5 – 8.4%, and for wind farms, 12.3-13.3%. Increasing the accuracy of renewable energy forecasting can positively affect the operation and planning of the central power system of Mongolia.
Downloads
Metrics
References
2. A. Khalyasmaa et al., “Prediction of solar power generation based on random forest regressor model,” in Proc. 2019 IEEE International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON), 2019, pp. 780-785, doi: 10.1109/SIBIRCON48586.2019.8958063
3. L. Visser, T. AlSkaif, and W. Van Sark, “Operational day-ahead solar power forecasting for aggregated PV systems with a varying spatial distribution,” Renewable Energy, vol. 183, pp. 267-282, 2022, doi: 10.1016/j.renene.2021.10.102
4. Z. O. A. Olaofe, “5-day wind speed and power forecasts using a layer recurrent neural network (LRNN),” Sustainable Energy Technologies and Assessments, vol. 6, pp. 1-24, 2014, doi: 10.1016/j.seta.2013.12.001
5. M. Santos and M. González, “Factors that influence the performance of wind farms,” Renewable Energy, vol. 135, pp. 643-651, 2019, doi: 10.1016/j.renene.2018.12.033
6. T. Ouyang, A. Kusiak, and Y. He, “Predictive model of yaw error in a wind turbine,” Energy, vol. 123, pp. 119-130, 2017, doi: 10.1016/j.energy.2017.01.150
7. M. Guermoui M et al., “A comprehensive review of hybrid models for solar radiation forecasting,” Journal of Cleaner Production, vol. 258, pp. 120357, 2020, doi: 10.1016/j.jclepro.2020.120357
8. H. T. Yang et al., “A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output,” IEEE transactions on sustainable energy, no. 3, vol. 5, pp. 917-926, 2014, doi: 10.1109/TSTE.2014.2313600
9. P. Gupta and R. Singh, “PV power forecasting based on data-driven models: a review,” International Journal of Sustainable Engineering, vol. 6(14), pp. 1733-1755, 2021, doi: 10.1080/19397038.2021.1986590
10. L. Zhao, S. N. Muhammad, M. J. Hafiz, and N. A. Ahmed, “A review on proliferation of artificial intelligence in wind energy forecasting and instrumentation management,” Environmental Science and Pollution Research, vol. 29, pp. 43690-43709, 2022, doi: 10.1007/s11356-022-19902-8
11. V. Manusov, P. Matrenin, M. Nazarov, and S. Beryozkina, “Short-Term Prediction of the Wind Speed Based on a Learning Process Control Algorithm in Isolated Power Systems,” Sustainability, vol. 2(15), pp. 1730, 2023, doi: 10.3390/su15021730
12. Tiwari and Seemant, “Wind speed forecasting methods for wind energy generation,” In Proc. 2022 IEEE 1st International Conference on Informatics (ICI), 2022, pp. 143-147, doi: 10.1109/ICI53355.2022.9786880
13. R. Meenal et al., “Weather forecasting for renewable energy system: a review,” Archives of Computational Methods in Engineering, vol. 5(29), pp. 2875-2891, 2022, doi: 10.1007/s11831-021-09695-3
14. C. Wang et.al., “A new wind power prediction method based on chaotic theory and Bernstein Neural Network,” Energy, vol. 117, pp. 259-271, 2016, doi: 10.1016/j.energy.2016.10.041
15. Li, Xiaoou, Juan Francisco Sabas, and Vicente Duarte Mendéz, “Wind energy forecasting using multiple ARIMA models,” In Proc. 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE), pp. 2034-2039, 2022, doi: 10.1109/CASE49997.2022.9926516
16. F. Marchesoni-Acland et al., “Analysis of ARMA solar forecasting models using ground measurements and satellite images,” In Proc. 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC), 2019, pp. 2445-2451, doi: 10.1109/PVSC40753.2019.8980821
17. A. Abdellatif et al., “Forecasting photovoltaic power generation with a stacking ensemble model,” Sustainability, no. 17, vol. 14. pp. 11083, 2022, doi: 10.3390/su141711083
18. A. P. Marugán et al, “A survey of artificial neural network in wind energy systems,” Applied energy, pp. 1822-1836, 2018, doi: 10.1016/j.apenergy.2018.07.084
19. S. Theocharides et al., “Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing,” Applied Energy, vol. 268, pp. 115023, 2020, doi: 10.1016/j.apenergy.2020.115023
20. Y. Zhang, and R. Li, “Short term wind energy prediction model based on data decomposition and optimized LSSVM,” Sustainable Energy Technologies and Assessments, vol. 52, pp. 102025, 2022, doi: 10.1016/j.seta.2022.102025
21. Khasanzoda, Nasrullo et al., “Regression model for predicting the speed of wind flows for energy needs based on fuzzy logic,” Renewable Energy, vol. 191, pp. 723-731, 2022, doi: 10.1016/j.renene.2022.04.017
22. A. E. Saleh et al. “A hybrid neuro-fuzzy power prediction system for wind energy generation,” International Journal of Electrical Power & Energy Systems, vol. 74, pp. 384-395, 2016, doi: 10.1016/j.ijepes.2015.07.039
23. D. A. Snegirev et al., “Day-ahead solar power plant forecasting accuracy improvement on the hourly basis,” In Proc. 2019 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), 2019, pp. 1088-1091. doi: 10.1109/EIConRus.2019.8657024
24. X. G. Agoua, R. Girard and G. Kariniotakis, “Short-term spatio-temporal forecasting of photovoltaic power production,” IEEE Transactions on Sustainable Energy, no. 2, vol. 9, pp. 538-546, 2017, doi: 10.1109/TSTE.2017.2747765
25. E. G. Kim, M. S. Akhtar and O. B. Yang, “Designing solar power generation output forecasting methods using time series algorithms,” Electric Power Systems Research, vol. 216, pp. 109073, 2023, doi: 10.1016/j.epsr.2022.109073
26. W. Yin W et al., “A novel non-iterative correction method for short-term photovoltaic power forecasting,” Renewable Energy, vol. 159, pp. 23-32, 2020, doi: 10.1016/j.renene.2020.05.134
27. H. Sharadga, S. Hajimirza and R. S. Balog, “Time series forecasting of solar power generation for large-scale photovoltaic plants,” Renewable Energy, vol. 150, pp. 797-807, 2020, doi: 10.1016/j.renene.2019.12.131
28. J. Shi et al., “Forecasting power output of photovoltaic systems based on weather classification and support vector machines,” IEEE Transactions on Industry Applications, vol. 3(48), pp. 1064-1069, 2012, doi: 10.1109/TIA.2012.2190816
29. L. Visser, T. AlSkaif and W. Van Sark, “Benchmark analysis of day-ahead solar power forecasting techniques using weather predictions,” In Proc. 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC), 2019, pp. 2111-2116, doi: 10.1109/PVSC40753.2019.8980899
30. S. Buhan, Y. Özkazanç and I. Çadırcı, “Wind pattern recognition and reference wind mast data correlations with NWP for improved wind-electric power forecasts,” IEEE Transactions on Industrial Informatics, vol. 3(12), pp. 991-1004, 2016, doi: 10.1109/TII.2016.2543004
31. T. Peng T et.al., “Negative correlation learning-based RELM ensemble model integrated with OVMD for multi-step ahead wind speed forecasting,” Renewable Energy, vol. 156, pp. 804-819, 2020, doi: 10.1016/j.renene.2020.03.168
32. Y. Li et.al., “Smart wind speed forecasting approach using various boosting algorithms, big multi-step forecasting strategy,” Renewable energy, vol. 135, pp. 540-553, 2019, doi: 10.1016/j.renene.2018.12.035
33. L. Wang, Y. Guo and X. Li, “Wind speed prediction using measurements from neighboring locations and combining the extreme learning machine and the AdaBoost algorithm,” Energy Reports, vol. 8, pp. 1508-1518, 2022, doi: 10.1016/j.egyr.2021.12.062
34. A. T. Dosdoğru and A. B. İpek, “Hybrid boosting algorithms and artificial neural network for wind speed prediction,” International Journal of Hydrogen Energy, no. 3, vol. 47, pp. 1449-1460, 2022, doi: 10.1016/j.ijepes.2021.107365
35. O. Abedinia et.al., “A multi-level model for hybrid short term wind forecasting based on SVM, wavelet transform and feature selection,” In Proc. 2022 IEEE International Conference on Environment and Electrical Engineering and 2022 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), 2022. pp. 1-6. doi: 10.1109/EEEIC/ICPSEurope54979.2022.9854519
36. Breiman Leo, “Random forests,” Machine learning, vol.45, pp. 5-32, 2001, doi: 10.1023/a:1010933404324
37. K. L. Jorgensen and H. R. Shaker, “Wind power forecasting using machine learning: State of the art, trends and challenges,” In Proc. 2020 IEEE 8th International Conference on Smart Energy Grid Engineering (SEGE), 2020, pp. 44-50, doi: 10.1109/SEGE49949.2020.9181870
38. Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of computer and system sciences, no. 1, vol. 55, pp. 119-139, 1997, doi: 10.1006/jcss.1997.1504
39. X. Guo et al., “Study on short-term photovoltaic power prediction model based on the Stacking ensemble learning,” Energy Reports, vol. 6, pp. 1424-1431, 2020, doi: 10.1016/j.egyr.2020.11.006
40. Q. T. Phan, Y. K. Wu and Q. D. Phan, “A hybrid wind power forecasting model with XGBoost, data preprocessing considering different NWPs,” Applied Sciences, no. 3, vol. 11, pp. 1100, 2021, doi: 10.3390/app11031100
41. https://open-meteo.com
42. A. Lahouar and J. B. H. Slama, “Hour-ahead wind power forecast based on random forests,” Renewable energy, vol. 109, pp. 529-541, 2017, doi: 10.1016/j.renene.2017.03.064
43. Anastasia G. Rusina, Tuvshin Osgonbaatar, Alina I. Stepanova and Pavel V. Matrenin, "Ensemble Machine Learning Model for Day Ahead Solar Power Forecasting for Mongolia Power System," In Proc. 2023 Belarusian-Ural-Siberian Smart Energy Conference (BUSSEC), 2023, pp. 84-87. doi: 10.1109/BUSSEC59406.2023.10296344.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Anastasia Rusina, Novosibirsk State Technical University
Doctor of Technical Sciences, Dean of the Faculty of Energy, Head of the Power Plants Department at Novosibirsk State Technical University (NSTU NETI). An Expert at the Russian Academy of Sciences, a full member of RNC CIGRE, a full member of IEEE, and a member of the organizing committee of 5 international conferences.
In 2006, she has received PhD degree; in 2013 DSc degree. Her research work includes 188 scientific publications, 3 monographs, and 6 state registration certificates for software. Areas of interest: load forecasting, hydropower plant operation modes modeling, targeted power distribution, optimization of plant operation modes.
Pavel Matrenin, Novosibirsk State Technical University
PhD in Computer Science, leading researcher at Ural Power Engineering Institute of Ural Federal University, associate professor at Power Supply System Department and senior researcher at the Research Laboratory for Analysis, Processing, and Presentation of Data of Novosibirsk State Technical University. A Member of IEEE, and a member of the organizing committee of 3 international conferences supported by IEEE.
In 2014 he has received master’s degree, in 2018 – PhD degree. His research work includes 130 scientific publications, 1 monograph, and more than 10 state registration certificates for software. Areas of interest: explainable artificial intelligence, safe machine learning, timeseries forecasting, computer vision, optimization and control of power systems.
Zagdkhorol Bayasgalan, Mongolian University of Science and Technology
PhD in Technical Science, Professor at the Department of Electrotechnique, Power Engineering School (PES), Mongolian University of Science and Technology(MUST). An Expert at the Mongolian National Council for Education Accreditation, a full member of IEEE, WSTEAM, and MATIYR.
In 1996 she has received master’s degree from PES, MUST, in 2004 – PhD degree from National Research University “Moscow Power Engineering Institute”. Areas of research: power system analysis, electricity market, modeling of power system regimes, optimization, smart grid, control and multidisciplinary research.
