پیش بینی کوتاه مدت سرعت باد با استفاده از الگوریتم های یادگیری ماشین
محورهای موضوعی : مهندسی برق قدرت
حمیدرضا صفا
1
,
علی اصغر قدیمی
2
1 - گروه مهندسی برق، دانشکده مهندسی، دانشگاه اراک، اراک، ایران
2 - گروه مهندسی برق، دانشکده مهندسی، دانشگاه اراک، اراک، ایران
کلید واژه: پیش‌بینی سرعت باد, تجزیه حالت متغیر, شبکه های عصبی مصنوعی,
چکیده مقاله :
تقاضای انرژی الکتریکی با توسعه صنعت به‌شدت افزایش یافته است، اما تأمین آن از سوخت‌های فسیلی مشکلاتی مانند گرمایش زمین و آلودگی محیط زیست را به دنبال دارد. با توجه به محدودیت و کاهش منابع فسیلی، یافتن جایگزین‌های پایدار ضروری است. در این میان، انرژی باد به دلیل هزینه کم و عدم تولید آلودگی، به عنوان یک منبع تجدیدپذیر مناسب برای تأمین انرژی الکتریکی مطرح می‌شود. با این حال، برای دستیابی به توان پایدار از نیروگاه‌های بادی، لازم است اطلاعات دقیقی از سرعت باد در آینده در دسترس باشد. پیش‌بینی سرعت باد به دلیل ماهیت تصادفی و متناوب آن بسیار دشوار است، در این مقاله، برای مقابله با این چالش و دستیابی به پیش‌بینی دقیق، از مدل ترکیبی شامل شبکه عصبی کانولوشنال موقتی و بازگشتی دوطرفه (TCN-BiLSTM) استفاده شده است. ابتدا، هایپرپارامترهای الگوریتم تجزیه حالت متغیر ، با استفاده از روش قدرتمند Optuna بهینه‌سازی شده‌اند. در مرحله بعد، داده‌های اصلی سرعت باد برای بهبود عملکرد مدل ترکیبی (TCN_BiLSTM) نرمالیزه شده و به الگوریتم تجزیه حالت متغیر داده شده‌اند تا به توابع مد ذاتي(IMF) تجزیه شوند. سپس هر IMFبه صورت جداگانه به مدل ترکیبی برای پیش‌بینی داده می‌شود. درآخر در نهایت، خروجی‌ها از حالت نرمال‌سازی خارج و ترکیب شده‌اند تا نتیجه نهایی به‌دست آید. با توجه به ارزیابی مدل ترکیبی با معیارهای آماری، نتایج نشان می‌دهد که مدل پیشنهادی دقت بالایی دارد. در این ارزیابی، ضریب تعیین برابر با 99.1٪، میانگین خطای مطلق برابر با 0.36 و ریشه میانگین مربعات خطا برابر با 0.48 به‌دست آمده است.
The demand for electrical energy has sharply increased with the development of industry. However, supplying this demand through fossil fuels leads to problems such as global warming and environmental pollution. Considering the limitations and depletion of fossil fuel resources, finding sustainable alternatives has become essential. Among these alternatives, wind energy stands out as a viable renewable source for electricity generation due to its low cost and lack of pollution. However, to achieve stable power generation from wind farms, accurate information about future wind speed is essential. Predicting wind speed is highly challenging due to its random and intermittent nature. In this paper, a hybrid model combining a Temporal Convolutional Network and Bidirectional Long Short-Term Memory (TCN-BiLSTM) is employed to address this challenge and achieve accurate predictions. First, the hyperparameters of the Variational Mode Decomposition (VMD) algorithm were optimized using the powerful Optuna method. Next, the original wind speed data were normalized to enhance the performance of the hybrid model (TCN-BiLSTM) and then fed into the VMD algorithm to be decomposed into Intrinsic Mode Functions (IMFs). Each IMF is then individually fed into the hybrid model for prediction. Finally, the outputs are denormalized and combined to obtain the final result. Based on the evaluation of the hybrid model using statistical metrics, the results indicate that the proposed model achieves high accuracy. In this evaluation, the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE) were found to be 99.1%, 0.36, and 0.48, respectively.
[1] Y. Zhao, L. Ye, Z. Li, X. Song, Y. Lang, and J. Su, "A novel bidirectional mechanism based on time series model for wind power forecasting," Applied energy, vol. 177, pp. 793-803, 2016. doi: 10.1016/j.apenergy.2016.03.096
[2] M. Tavoosi, F. E. Heydarian, M. H. Amirioun, and M. M. Parsa, "A Review on the Technical Challenges of Connecting Wind Energy Conversion Systems to the Grid," 2022. doi: 10.30486/teeges.2022.1965932.1031
[3] J. Wan, G. Ren, J. Liu, Q. Hu, and D. Yu, "Ultra-short-term wind speed prediction based on multi-scale predictability analysis," Cluster Computing, vol. 19, pp. 741-755, 2016. doi: 10.1007/s10586-016-0554-0
[4] D. Song et al., "New perspectives on maximum wind energy extraction of variable-speed wind turbines using previewed wind speeds," Energy conversion and management, vol. 206, p. 112496, 2020. doi: 10.1016/j.enconman.2020.112496
[5] J. Zhao, Y. Guo, X. Xiao, J. Wang, D. Chi, and Z. Guo, "Multi-step wind speed and power forecasts based on a WRF simulation and an optimized association method," Applied energy, vol. 197, pp. 183-202, 2017. doi: 10.1016/j.apenergy.2017.04.017
[6] H. Verbois, R. Huva, A. Rusydi, and W. Walsh, "Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning," Solar Energy, vol. 162, pp. 265-277, 2018. doi: 10.1016/j.solener.2018.01.007
[7] V. Hoolohan, A. S. Tomlin, and T. Cockerill, "Improved near surface wind speed predictions using Gaussian process regression combined with numerical weather predictions and observed meteorological data," Renewable Energy, vol. 126, pp. 1043-1054, 2018. doi: 10.1016/j.renene.2018.04.019
[8] M. Gan, H. Peng, X. Peng, X. Chen, and G. Inoussa, "A locally linear RBF network-based state-dependent AR model for nonlinear time series modeling," Information Sciences, vol. 180, no. 22, pp. 4370-4383, 2010. doi: 10.1016/j.ins.2010.07.012
[9] E. Grigonytė and E. Butkevičiūtė, "Short-term wind speed forecasting using ARIMA model," Energetika, vol. 62, no. 1-2, 2016. doi: 10.6001/energetika.v62i1-2.3313
[10] Z. Lu, S. Lu, M. Xu, and B. Cui, "A robust stochastic stability analysis approach for power system considering wind speed prediction error based on Markov model," Computer Standards & Interfaces, vol. 75, p. 103503, 2021. doi: 10.1016/j.csi.2020.103503
[11] Z. Zhou, Y. Dai, J. Xiao, M. Liu, J. Zhang, and M. Zhang, "Research on Short-Time Wind Speed Prediction in Mountainous Areas Based on Improved ARIMA Model," Sustainability, vol. 14, no. 22, p. 15301, 2022. doi: 10.3390/su142215301
[12] E. Erdem and J. Shi, "ARMA based approaches for forecasting the tuple of wind speed and direction," Applied Energy, vol. 88, no. 4, pp. 1405-1414, 2011. doi: 10.1016/j.apenergy.2010.10.031
[13] G. Santamaría-Bonfil, A. Reyes-Ballesteros, and C. Gershenson, "Wind speed forecasting for wind farms: A method based on support vector regression," Renewable Energy, vol. 85, pp. 790-809, 2016. doi: 10.1016/j.renene.2015.07.004
[14] Z. Qu, W. Mao, K. Zhang, W. Zhang, and Z. Li, "Multi-step wind speed forecasting based on a hybrid decomposition technique and an improved back-propagation neural network," Renewable energy, vol. 133, pp. 919-929, 2019. doi: 10.1016/j.renene.2018.10.043
[15] Z. Ma, T. Wu, S. Guo, H. Wang, G. Xu, and S. Aziz, "An integrated prediction model based on meta ensemble learning for short‐term wind speed forecasting," IET Renewable Power Generation, 2024. doi: 10.1049/rpg2.13016
[16] Y. Ding, X.-W. Ye, and Y. Guo, "A multistep direct and indirect strategy for predicting wind direction based on the EMD‐LSTM model," Structural Control and Health Monitoring, vol. 2023, no. 1, p. 4950487, 2023. doi: 10.1155/2023/4950487
[17] Y. Sun, J. Yang, X. Zhang, K. Hou, J. Hu, and G. Yao, "An Ultra-short-term wind power forecasting model based on EMD-EncoderForest-TCN," IEEE Access, 2024. doi: 10.1109/ACCESS.2024.3373798
[18] D. Niu, Y. Liang, and W.-C. Hong, "Wind speed forecasting based on EMD and GRNN optimized by FOA," Energies, vol. 10, no. 12, p. 2001, 2017. doi: 10.3390/en10122001
[19] D. Zhang, C. Cai, S. Chen, and L. Ling, "An improved genetic algorithm for optimizing ensemble empirical mode decomposition method," Systems Science & Control Engineering, vol. 7, no. 2, pp. 53-63, 2019. doi: 10.1080/21642583.2019.1627598
[20] A. Kang, Q. Tan, X. Yuan, X. Lei, and Y. Yuan, "Short‐Term Wind Speed Prediction Using EEMD‐LSSVM Model," Advances in Meteorology, vol. 2017, no. 1, p. 6856139, 2017. doi: 10.1155/2017/6856139
[21] K. Jaseena and B. C. Kovoor, "EEMD-based Wind Speed Forecasting system using Bidirectional LSTM networks," in 2021 International Conference on Computer Communication and Informatics (ICCCI), 2021, pp. 1-9: IEEE. doi: 10.1109/ICCCI50826.2021.9402648
[22] K. Gezici, O. M. Katipoğlu, and S. Şengül, "Hybrid machine learning models for groundwater level prediction in a snow‐dominated region: An evaluation of EEMD, VMD and EWT decomposition techniques," Hydrological Processes, vol. 38, no. 5, p. e15169, 2024. doi: 10.1002/hyp.15169
[23] A. L. Wood, A. Simon, P. W. Downs, and C. R. Thorne, "Bank‐toe processes in incised channels: The role of apparent cohesion in the entrainment of failed bank materials," Hydrological Processes, vol. 15, no. 1, pp. 39-61, 2001. doi: 10.1002/hyp.15169
[24] Y. Zhang, Y. Zhao, C. Kong, and B. Chen, "A new prediction method based on VMD-PRBF-ARMA-E model considering wind speed characteristic," Energy Conversion and Management, vol. 203, p. 112254, 2020. doi: 10.1016/j.enconman.2019.112254
[25] A. A. Abdoos, "A new intelligent method based on combination of VMD and ELM for short term wind power forecasting," Neurocomputing, vol. 203, pp. 111-120, 2016. doi: 10.1016/j.neucom.2016.03.054
[26] M. Hassanali, M. Soltanaghaei, T. Javdani Gandomani, and F. Zamani Boroujeni, "Software development effort estimation using boosting algorithms and automatic tuning of hyperparameters with Optuna," Journal of Software: Evolution and Process, p. e2665, 2024. doi: 10.1002/smr.2665
[27] J. Zhu, L. Su, and Y. Li, "Wind power forecasting based on new hybrid model with TCN residual modification," Energy and AI, vol. 10, p. 100199, 2022. doi: 10.1016/j.egyai.2022.100199
[28] R. Zhu, W. Liao, and Y. Wang, "Short-term prediction for wind power based on temporal convolutional network," Energy Reports, vol. 6, pp. 424-429, 2020. doi: 10.1016/j.egyr.2020.11.219
[29] S. Moalem, R. MP Ahari, G. Shahgholian, M. Moazzami, and S. M. Kazemi, "A Hybrid Method for Long-Term Demand Forecasting in the Electrical Energy Supply Chain of Basic Metal Production Industries in the Presence of Incomplete Data," Technovations of Electrical Engineering in Green Energy System, vol. 2, no. 1, pp. 117-139, 2023. doi: 10.30486/teeges.2023.1974408.1051
[30] A. Saeed et al., "Hybrid bidirectional LSTM model for short-term wind speed interval prediction," IEEE Access, vol. 8, pp. 182283-182294, 2020. doi: 10.1109/ACCESS.2020.3027977