ارائه یک الگوریتم فراابتکاری ترکیبی به منظور پیش بینی کوتاه مدت سرعت باد

محورهای موضوعی : انرژی های تجدیدپذیر

هومن گدری ¹ , حمیدرضا اکبری ² , سمیه موسوی ³ , زهره بهشتی پور ⁴

1 - گروه مهندسی برق- واحد یزد، دانشگاه آزاد اسلامی، یزد، ايران
2 - گروه مهندسی برق- واحد یزد، دانشگاه آزاد اسلامی، یزد، ايران
3 - گروه مهندسی صنایع- دانشگاه میبد، میبد، ايران
4 - گروه مهندسی برق- واحد یزد، دانشگاه آزاد اسلامی، یزد، ايران

تاریخ دریافت : 1403/03/08 تاریخ پذیرش : 1403/07/29 تاریخ انتشار : 1404/10/01

کلید واژه: روش گروهی مدل‌سازی داده‌ها, الگوریتم بهینه ساز جستجوی عروس دریایی مصنوعی, پیش بینی کوتاه مدت سرعت باد.,

چکیده مقاله :

تخمین نزدیک به واقعیت منابع انرژی تجدیدپذیر که دارای عدم قطعیت هستند امری دشوار و پیچیده است. در برنامه ریزی بهینه سیستم قدرت نیازمند روشی هستیم که خطای تخمینی داده‌ها را به حداقل برساند. در این میان پیش‌بینی کوتاه مدت سرعت باد می‌تواند منجر به برنامه ریزی دقیق‌تر سیستم قدرت بخصوص ریزشبکه‌ها شود. رویکردهای متفاوتی درتعیین عدم قطعیت توان بادی وجود دارد که در جهت دقت بیشتر هر روزه درحال بهینه شدن هستند. در این مقاله آموزش روش گروهی مدل سازی داده‌ها با استفاده از الگوریتم بهینه ساز جستجوی عروس دریایی مصنوعی انجام می‌شود. این مدل ترکیبی، پیچیدگی روش‌های مشابه را ندارد و در رسیدن به پاسخ بهینه نسبت به دیگر مدل‌های پیش‌بینی کوتاه مدت زودتر همگرا شده و در زمان کمتری به پاسخ مطلوب می‌رسد. برای ارزیابی دقت مدل پیشنهادی، از داده‌های واقعی شهرستان کرمان برای پیش بینی کوتاه مدت سرعت باد این منطقه استفاده شده است. نتایج این پیش بینی با روش‌های مشابه GMDH-PSO، ماشین بردار پشتیبان و شبکه عصبی حافظه‌ی کوتاه‌ مدت طولانی مقایسه گردیده است. در ارزیابی مدل پیشنهادی معیار میانگین درصد خطای مطلق بمقدار 7.5807 را دارد که نسبت به مدل‌های مشابه مورد ارزیابی عملکرد بهتری را نشان می‌دهد. همچنین مدل پژوهش مقادیر 0.9923 و 0.3891 برای معیارهای ضریب تعیین امتیاز و مجذور میانگین مربعات خطا کسب کرده است.

چکیده انگلیسی:

Among renewable energies, the short-term forecast of wind energy helps significantly in determining the size of wind energy resources. Short-term forecast of wind speed can lead to more accurate planning of power systems. There are different approaches in determining the uncertainty of wind turbines, which are being optimized for more accuracy every day. In this study, the training of the group method of data modeling is done using the artificial jellyfish search optimization algorithm. This combined model does not have the complexity of similar methods, and in reaching the optimal answer, it converges earlier than other short-term prediction models and reaches the desired answer in less time. To evaluate the accuracy of the proposed method, the real data of Kerman city have been used to predict the short-term wind speed of this region. The results of this prediction have been compared with support vector machine and long short-term memory neural network. In the evaluation of the proposed model, the average percentage of absolute error has a value of 7.5807, which shows a better performance than the similar models evaluated. The mentioned error based on the average value of absolute error percentage has been reduced by 4.2904 compared to the optimal support vector machine model and 5.6193 compared to the optimal a Long short-term memory model respectively. Also, the evaluation of the model includes the criteria of the rating coefficient and the standard of the mean square error.

منابع و مأخذ:

[1] L. Hirth, "The market value of variable renewables: The effect of solar wind power variability on their relative price", Energy Econ, vol. 38, pp. 218-236, July. 2013 (doi.org/10.1016/j.eneco.2013.02.004)
[2] F. Bouffard, FD. Galiana, "Stochastic security for operations Planning with Significant Wind Power Generation", IEEE Trans Power Syst, vol. 23, pp. 306 – 316, May. 2008 (doi: 10.1109/TPWRS.2008.919318)
[3] Y. Zhang, N. Gatsis, GB. Giannakis, "Robust energy management for microgrids with high-penetration renewables", IEEE Trans Sust Energy, vol. 4, pp. 944-953, Oct. 2013 (doi:10.1109/TSTE.2013.22551135)
[4] G. Tang, Y. Wu, C. Li,P. Wong, Z. Xiao, X. An, "A Novel wind speed interval prediction based on error prediction method", IEEE Transactions on Industrial Informatics, Vol. 16, pp. 6806 – 6815, Nov. 2020 (doi: 10.1109/TII.2020.2973413)
[5] B. Huang, Y. Liang, X. Qiu, "Wind power forecasting using attention-based recurrent neural networks: A comparative Study", IEEE Access, Vol 9, pp. 40432 – 40444, March. 2021, (doi: 10.1109/ACCESS.2021.3065502)
[6] C. Tu, W. Tsai, C Hong ,W Lin, "Short-Term solar power forecasting via general regression neural network with grey wolf optimization", Energies, vol. 15, pp. 6624, Sep 2022 (doi.org/10.3390/en15186624)
[7] M. Afrozeh,H.Abdolmohamadi,M. Nazari, "Apply a mutation in gray wolf optimization algorithm to Solve the Economic-Environmental Dispatch Problem of Integrated Power Plants Including Thermal and wind “, Journal of Intelligent Procedures in Electrical Technology, Vol. 14, pp. 59-76, Winter. 2022
[8] E. Brenjkar, " Evaluation of the performance of artificial neural networks integrated with whale optimization and ant colony optimization algorithms in estimating the drilling rate of penetration and compare with simple neural networks and mathematical conventional models", Modeling in Engineering, Vol. 19, pp. 115-135, summer. 2021
[9] E. Alves, M. Lopes, F. Sales, A. Balieiro, "A GMDH Approach for Forecast Monthly Rainfall in Southeast of Para", IEEE Latin America Transactions, Vol. 21, Pp. 707–714, June. 2023 (doi: 10.1109/TLA.2023.10172135)
[10] B. Badyalina, AF. Azimi, "Data-driven models for wind speed forecasting in malacca state", Matematika MJIM, vol 38, Num. 2, pp. 125–139, Aug. 2022 (https:// matematika. utm.my/index.php /matematika/article/view/1404)
[11] Y. Zhang, Y. Zhao, S. Gao, "A novel hybrid model for wind speed prediction based on VMD and neural network considering atmospheric uncertainties", IEEE Access, Vol. 7, pp. 60322 - 60332, May. 2019 (doi: 10.1109/ACCESS.2019.2915582)
[12] S. Makhloufi, G. Gopalakrishna Pillai, ”Wind speed and wind power forecasting using wavelet denoising-GMDH neural network”, 2017 5th International Conference on Electrical Engineering - Boumerdes (ICEE-B), (doi: 10.1109/ICEE-B.2017.8192155)
[13] Chongqing Shi1, Xiaoli Zhang, "Recurrent neural network wind power prediction based on variational modal decomposition improvement", AIP Advances 13, Issue 2, Feb. 2023 (doi.org/10.1063/5.0135711)
[14] Bilin Shao ,Dan Song ,Genqing Bian , Yu Zhao," Wind speed forecast based on the LSTM neural network optimized by the firework algorithm", Hindawi Advances in Materials Science and Engineering, Vol. 2021, Article. ID 4874757 (doi.org/10.1155/2021/4874757)
[15] Y. wang, D. wang, Y. tang, "Clustered hybrid wind power prediction model based on ARMA, PSO-SVM, and clustering methods", IEEE access, Vol. 8, Jan. 2020 (doi: 10.1109/ACCESS.2020.2968390)
[16] M. elsaraiti, A. Merabet, " Application of Long-Short-Term-Memory recurrent neural networks to forecast wind speed", Appl. Sci, Oct. 2021(https://doi.org/10.3390/app11052387)
[17] A. Khosravi, L. Machado, R.O. Nunes, "Time-series prediction of wind speed using machine learning algorithms: A case study Osorio wind farm, Brazil", Applied Energy, vol. 224, pp. 550-566, , Aug. 2018 (doi.org/10.1016/j.apenergy.2018.05.043)
[18] M. Liua, Z. Caoc, J. Zhanga, L. Wanga, C. Huanga, X. Luoa, " Short-term wind speed forecasting based on the Jaya-SVM model", Electrical Power and Energy systems (Elsevier), Volume 121, Feb 2020, doi.org/10.1016/j.ijepes.2020.106056
[19] L. Jinghua,L Yongsheng ,Y. Shuhui, "Mid-long term load forecasting model based on support vector machine optimized by improved sparrow search algorithm", Energy Reports, vol. 8, pp. 491–497, Aug 2022 (doi.org/10.1016/j.egyr.2022.02.188)
[20] A. Heydari,D. Astiaso Garcia,F. Keynia,F. Bisegna,L. De Santoli, "A novel composite neural network based method for wind and solar power forecasting in microgrids", Applied Energy, vol. 251, issue 113353, Oct. 2019 (doi.org/10.1016/j.apenergy.2019.113353)
[21] A. Heydari , M. Majidi Nezhad, M. Neshat, D. Astiaso Garcia, F. Keynia, L. Santoli, L. Bertling Tjernberg, ”A combined fuzzy GMDH neural network and grey wolf optimization application for wind turbine power production forecasting considering SCADA data,” energies,14, pp. 3459, June 2021 (doi.org/10.3390/en14123459)
[22] M.FARHAT,S.KAMEL,A.M.ATALLAH1,B. KHAN. "Optimal power flow solution Based on Jellyfish
Search Optimization Considering Uncertainty of Renewable Energy Sources". IEEE Access,Volume: 9,July 2021,pp 100911 – 100933,DOI: 10.1109/ACCESS.2021.3097006
[23] J.Sheng Chou, D.Nhat Truong. "A novel metaheuristic optimizer inspired by behavior of
jellyfish in ocean". Applied Mathematics and Computation , Vol. 389, pp. 125535, Jan. 2021 (doi.org/10.1016/j.amc.2020.125535)
[24] A. Alam Preeti Verma, M. Tariq , A. Sarwar , B.Alamri, N. Zahra,S. Urooj. "Jellyfish search optimization algorithm for MPP tracking of PV system”. MDPI sustainability, Vol. 13, pp. 11736, 2021(doi.org/10.3390/su132111736)
[25] A.G. Ivakhnenko, "Polynomial theory of complex systems", IEEE Transactions on systems, vol, SMC-1, pp. 364–378, 1971 (doi: 10.1109/TSMC.1971.4308320)
[26] E. Dodangeh,M. Panahi,S. Lee,D. Tien Bui, “Novel hybrid intelligence models for flood-susceptibility prediction: Meta optimization of the GMDH and SVR models with the genetic algorithm and harmony search“, Journal of Hydrology, Vol 590, pp. 125423, Nov. 2020 (doi.org/10.1016/j.jhydrol.2020.125423)
[27] YU.P Zaychenko,I.O. Zayets, “The fuzzy group method of data handling and its application to the problems of the macroeconomic indexes forecasting” ,Systems Analysis Modelling Simulation,vol 43,Oct 2010,Issue 10,pp. 1321-1329,doi.org/10.1080/02329290290023349.
[28] A. Sabziparvar,M. Bayat, "Evaluation of accuracy of artificial neural network and neural-fuzzy methods in simulating total solar radiation", Iranian Journal of Physics Research, vol. 10, Vol. 4, winter. 2019
[29] LIJUAN ZHU AND WEI HU, “Short term wind speed prediction based on VMD and DBN combined model optimized by improved sparrow intelligent algorithm", IEEE Access, Vol. 10, pp. 92259 – 92272, Aug 2022, (doi: 10.1109/ACCESS.2022.3202970)
[30] V. Vahidinasab, H. Sohrabi Vafa, ”Wind power forecasting by a new hybrid forecast engine composed of GA/EPSO-Based mutual information and group method of data handling (GMDH)” , Scientific Journal of Computational Intelligence in Electrical Engineering, Vol. 9, Pages 1-14, Sep. 2018 (doi: 10.22108/isee.2018.89972.0)
[31] E. Elattar, I. Taha, ”Improved short term wind power prediction using a combined locally weighted GMDH and KPCA”, International Journal of Scientific & Engineering Research, Vol 4, pp1216, Aug. .2013