Short Term Wind Speed Forecast Using Recurrent Neural Networks for Wind/Battery Energy Management
Keywords:
wind power, forecasting, recurrent neural network, managementAbstract
As the enhanced energy crisis, wind power generated through wind turbines, widely known as a bright renewable energy source, is being mostly utilized. As a result, wind energy forecasting, notably wind speed forecasting is crucial for power energy management and production-consummation balance. Nevertheless, wind speed prediction is deeply challenging due to its non-stationary and nonlinear character. The main research aim to develop an effective paradigm for wind speed estimation based on recurrent neural network. Three topologies are proposed namely the modified Elman neural network, the Jordan neural network and the hybrid model that combines the latest cited networks. The mentioned forecasting models are evaluated through various statistical metrics mainly the normalized root mean squared error, the mean absolute percentage error and the correlation factor. The experimental results show that the predictors performed satisfactory forecasts. While, the efficiency index is slightly finer using the hybrid algorithm with an R-ratio equal to 99%. The estimated wind power is derived through the forecasted wind speed via a mathematical model. The derived generated power is utilized for Wind/Battery energy management in isolated area. The proposed supervision algorithm raises the wind power use to 92%.
Downloads
References
Z. Maheshwari, K. Kengne and O. Bhat, “A comprehensive review on wind turbine emulators,” Renewable and Sustainable Energy Reviews, Vol. 180, p. 113297, Jul. 2023, doi: 10.1016/j.rser.2023.113297.
W. Yang, M. Hao and Y. Hao , “Innovative ensemble system based on mixed frequency modeling for wind speed point and interval forecasting,” Information Sciences, Vol. 622, pp. 560-586, doi: 10.1016/j.ins.2022.11.145.
S. M. Valdivia-Bautista, J. A. Domínguez-Navarro, M. Pérez-Cisneros, C. J. Vega-Gómez and B. Castillo-Téllez, “Artificial intelligence in wind speed forecasting: A review,” Energies, vol. 16(5), p. 2457, March 2024, doi: 10.3390/en16052457.
Y. M. Zhang and H. Wang, “Multi-head attention-based probabilistic CNN-BiLSTM for day-ahead wind speed forecasting,” Energy, Vol. 278, p. 127865, Sept 2023, doi: 10.1016/j.energy.2023.127865.
S. Sheoran and S. Pasari, S, “Efficacy and application of the window-sliding ARIMA for daily and weekly wind speed forecasting,” Journal of Renewable and Sustainable Energy, Vol. 14(5), p. 053305, Oct 2022, doi: 10.1063/5.0108847.
L. P. Joseph, R. C. Deo, R. Prasad, S. Salcedo-Sanz, N. Raj and J. Soar, “Near real-time wind speed forecast model with bidirectional LSTM networks,” Renewable Energy, Vol. 204, pp. 39-58, Jan 2023, doi: 10.1016/j.renene.2022.12.123.
Y. Amellas, O. El Bakkali, A. Djebli and A. Echchelh, “Short-term wind speed prediction based on MLP and NARX networks models,” Indonesian Journal of Electrical Engineering and Computer Science, Vol. 18(1), pp. 150-157, Apr 2020, doi: 10.11591/ijeecs.v18.i1.
M. Madhiarasan, “Accurate prediction of different forecast horizons wind speed using a recursive radial basis function neural network,” Protection and Control of Modern Power Systems, Vol. 5(3), pp. 1-9, Oct 2020, doi: 10.1186/s41601-020-00166-8.
J. Ding, G. Chen, Y. Huang, Z. Zhu, K. Yuan and H. Xu, “Short-term wind speed prediction based on CEEMDAN-SE-improved PIO-GRNN model,” Measurement and Control, Vol. 54(1-2), pp. 73-87, Nov 2021, doi: 10.1177/0020294020981400.
M. Motahari-Nezhad, “Elman and Jordan neural networks for prediction of transient thermal contact for engine exhaust valve,” Automotive Science and Engineering, Vol. 13(1), pp. 4051-4061, March 2023, doi: 10.22068/ase.2023.633.
E. Fedorov, O. Nechyporenko and T. Neskorodieva, “Method for Creating a Computer Agent Based on the Jordan-Elman Neural Network for Supply Chains,” In 4th International Workshop on Intelligent Information Technologies and Systems of Information Security, Vol. 3373, pp. 34-47, March 2023.
D. Bujak, S. Ilic, H. Miličević and D. Carević, , “Wave Runup Prediction and Alongshore Variability on a Pocket Gravel Beach under Fetch-Limited Wave Conditions,” Journal of marine science and engineering, Vol. 11(3), p. 614, March 2023, doi: 10.3390/jmse11030614.
S. Chen, W .Feng, L. He, W. Xiao, H .Feng, Q. Yu, Q. and J. He, “Parameterization of the Ångström–Prescott formula based on machine learning benefit estimation of reference crop evapotranspiration with missing solar radiation data,” Hydrological Processes, Vol. 38(2), p. 15091, Feb 2024, doi: 10.1002/hyp.15091
A. Petrović and Z. Đurišić, “Genetic algorithm based optimized model for the selection of wind turbine for any site-specific wind conditions,” Energy, Vol. 236, p. 121476, Dec 2021, doi: 10.1016/j.energy.2021.121476.
I. Ouachani, A. Rabhi, I. Yahyaoui, B. Tidhaf, T. F. Tadeo, “Renewable energy management algorithm for a water pumping system,” Energy Procedia, Vol. 111, pp. 1030-1039, Mar 2017, doi: 10.1016/j.egypro.2017.03.266.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
