Wind Speed Forecasting Based on Secondary Decomposition and LSTM | [International Journal of Communication Networks and Information Security • 2024]

Author(s):

1. Ari Shawkat Tahir: University of Zakho,Zakho,Iraq

2. Adnan Mohsin Abdulazeez: Duhok Polytechnic University, Duhok, Iraq

3. Ismael Ali Ali: Duhok Polytechnic University, Duhok, Iraq

Abstract:

Improving the reliability of wind speed forecasting is critical for optimizing wind power generation efficiency and grid stability. Accurate predictions enhance operational planning and decisionmaking, thereby supporting the sustainability and economic viability of wind energy. Given the inherently stochastic and noisy nature of wind, implementing a preprocessing step is essential to obtain more accurate wind speed data. Decomposition techniques are recognized as essential preprocessing, which effectively transform unstable wind speed data into multiple regular components. This study introduced a hybrid wind speed forecasting model that integrates a secondary decomposition algorithm with a Long Short-Term Memory (LSTM) algorithm. For the decomposition part, Wavelet Decomposition (WA) was first used to extract the low-frequency part from the original wind data. Then, the Symplectic Geometry Mode Decomposition (SGMD) decomposes the rest of the high-frequency components. The predictive phase of the model utilizes the LSTM algorithm. Experimental results demonstrate that the proposed secondary decomposition method significantly outperforms single decomposition models. Additionally, the superiority of the proposed hybrid model is evident when compared with other hybrid models. The proposed model demonstrates substantial improvements in prediction accuracy of a utilized dataset by 37%, 13%, and 17% reduction in terms of MAPE, RMSE, and MAE respectively for 1-3 steps of the forecast. Overall, the proposed model provides more accurate and reliable wind speed forecasts compared to other benchmark models.

Page(s): 1-103

DOI: DOI not available

Published: Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: 3, Year: 2024

Keywords:

LSTM , Wind Speed Forecasting , Secondary Decomposition , Wavelet Decomposition , SGMD

References:

[1] Liu H.,Mi X.,Li Y. .2017 .Wind speed forecasting method based on deep learning strategy using empirical wavelet transform, long short term memory neural network and Elman neural network,” Energy Convers. , 11 : 498-514.

[2] Kou P.,Liang D.,Gao F.,Gao L. .2014 .Probabilistic wind power forecasting with online model selection and warped gaussian process,” Energy Convers. , 04 : 649-663.

[3] Zuluaga C. D.,Álvarez M. A. .2015 .Short-term wind speed prediction based on robust Kalman filtering: An experimental comparison. ” Appl. Energy, 07 : 321-330.

[4] Shi Z.,Liang H.,Dinavahi V. .2017 .Direct interval forecast of uncertain wind power based on recurrent neural networks. ” IEEE Trans. Sustain. Energy, 2774195(3) : 1177-1187.

[5] Hu X. .2007 .Study on the time-series wind speed forecasting of the wind farm based on neural networks,” Energy Conserv. , : .

[6] Zhang J.,Cai X. .2012 .Short-term wind speed prediction based on grey system theory model in the region of China,”. Przegląd Elektrotechniczny, : 67-71.

[7] Zhang Y.,Zhao Y.,Kong C.,Chen B. .2019 .A new prediction method based on VMD-PRBF-ARMA-E model considering wind speed characteristic,” Energy Convers. , 112254 : 112254.

[8] Mohammed M. A.,Ahmed L. A. .2023 .Forecasting wind speed using the proposed wavelet neural network,” Discret. Nat. Soc., : .

[9] Chen X.,Li Y.,Zhang Y.,Ye X.,Xiong X.,Zhang F. .2021 .A novel hybrid model based on an improved seagull optimization algorithm for short-term wind speed forecasting. ” Processes, 9(2) : .

[10] Hanoon M. S. .2022 .Wind speed prediction over Malaysia using various machine learning models: Potential renewable energy source. ” Eng. Appl. Comput. Fluid Mech., 2103588(1) : 1673-1689.

[11] Tran Anh D.,Dang T. Duc,Pham Van S. .2019 .Improved rainfall prediction using combined pre-processing methods and feed-forward neural networks. ” J, 2(1) : 65-83.

[12] Ali T. H.,Mahmood S. H.,Wahdi A. S. .2022 .Using proposed hybrid method for neural networks and wavelet to estimate time series model,”. Tikrit J. Adm. Econ. Sci., 18(3) : 432-448.

[13] Li Z. .2022 .“Prediction of river sediment transport based on wavelet transform and neural network model. ” Appl. Sci., 12(2) : .

[14] Ö .2023 .Prediction of wind power with machine learning models. ” Appl. Sci., 13(20) : 11455.

[15] Ciechulski T.,Osowski S. .2024 .Wind power short-term time-series prediction using an ensemble of neural networks. ” Energies, 17(1) : .

[16] Liu H.,Mi X.,Li Y. .2018 .An experimental investigation of three new hybrid wind speed forecasting models using multi-decomposing strategy and ELM algorithm. ” Renew. Energy, 02 : 694-705.

[17] Sun S.,Wei L.,Xu J.,Zhenni and J. .2019 .A New wind speed forecasting modeling strategy using two-stage decomposition, feature selection. , 12 : 334.

[18] Fu W.,Zhang K.,Wang K.,Wen B.,Fang P.,Zou F. .2020 .A hybrid approach for multi-step wind speed forecasting based on two-layer decomposition, improved hybrid DE-HHO optimization. , 09 : 211-229.

[19] Dong Y.,Li C.,Shi H.,Zhou P. .2024 .Short-term probabilistic wind speed predictions integrating multivariate linear regression and generative adversarial network methods,” Atmosphere (Basel). , 15(3) : .

[20] Grossmann A.,Morlet J. .1984 .Decomposition of hardy functions into square integrable wavelets of constant shape,”. SIAM J. Math. Anal., 15(4) : 723-736.

[21] Shaker A. N.,Bi-Orthogonal Wavelets .55 .Comparison between Orthogonal. , 55(2) : 2724.

[22] Dolatabadi A.,Abdeltawab H.,Y. A.-R. I. Mohamed H. .2020 .Hybrid deep learning-based model for wind speed forecasting based on DWPT and bidirectional LSTM network,” IEEE Access. , 3047077 : 229219-229232.

[23] Tran V. G.,Grieu S.,Polit M.,Tran Q. T.,Tran H. L.,EWEC H. L. .2009 .Forecasting of wind speed using wavelets analysis and cascadecorrelation neural networks. ” Eur. Wind Energy Conf. Exhib, 6 : 4027-4036.

[24] Mallat S. G. .1989 .A theory for multiresolution signal decomposition: the wavelet representation. ” IEEE Trans. Pattern Anal. Mach, 11(7) : 674-693.

[25] Mandal P.,Zareipour H.,Res Int. J. Energy .2014 .Forecasting aggregated wind power production of multiple wind farms using hybrid wavelet-PSO-NNs,”. , 38(13) : 1654-1666.

[26] Addison P. S. .2016 .Introductory theory and applications in science, engineering, medicine and finance," Boca Raton, FL. , : .

[27] Pan H.,Yang Y.,Li X.,Zheng J.,Process Mech. Syst. Signal .2018 .Symplectic geometry mode decomposition and its application to rotating machinery compound fault diagnosis,”. , 05 : 189-211.

[28] Hochreiter S.,Schmidhuber J. .1997 .“Long short-term memory,” Neural Comput. , 9(8) : 1735-1780.

[29] Yan Y.,Wang X.,Ren F.,Shao Z.,Tian C. .2022 .Wind speed prediction using a hybrid model of EEMD and LSTM considering seasonal features,” Energy Reports. , 07 : 8965-8980.

[30] Landi F.,Baraldi L.,Cornia M.,Cucchiara R. .2021 .Working Memory Connections for LSTM,” Neural Networks. , 08 : 334-341.

[31] .2022 .-speed-prediction-dataset/data. , : .

[32] Yin H. .2017 .“An effective secondary decomposition approach for wind power forecasting using extreme learning machine trained by crisscross optimization,” Energy Convers. , 08 : 108-121.

[33] Liu H.,Duan Z.,Han F.,Li Y. .2017 .Big multi-step wind speed forecasting model based on secondary decomposition, ensemble method and error correction algorithm,” Energy Convers. , 11 : 525-541.

[34] Sun W.,Tan B.,Wang Q. .2021 .“Multi-step wind speed forecasting based on secondary decomposition algorithm and optimized back propagation neural network. ” Appl. Soft Comput., 107894 : 107894.

[35] Peng T.,Zhou J.,Zhang C.,Zheng Y. .2017 .“Multi-step ahead wind speed forecasting using a hybrid model based on two-stage decomposition technique and AdaBoost-extreme learning machine,” Energy Convers. , 10 : 589-602.

Citations

Downloads

Views