Decomposition-based hybrid wind speed forecasting model using deep bidirectional LSTM networks

被引:205
作者
Jaseena, K. U. [1 ,2 ]
Kovoor, Binsu C. [1 ]
机构
[1] Cochin Univ Sci & Technol, Sch Engn, Div Informat Technol, Kochi, Kerala, India
[2] MES Coll Marampally, Dept Comp Applicat, Kochi, Kerala, India
关键词
Wind speed Forecasting; Deep Learning; Data Decomposition Techniques; Bidirectional Long Short Term Memory; Networks; Empirical Wavelet Transform; SINGULAR SPECTRUM ANALYSIS; EMPIRICAL WAVELET TRANSFORM; TIME-SERIES PREDICTION; ANN MODELS; ENSEMBLE; ARIMA;
D O I
10.1016/j.enconman.2021.113944
中图分类号
O414.1 [热力学];
学科分类号
摘要
The goal of sustainable development can be attained by the efficient management of renewable energy resources. Wind energy is attracting attention worldwide due to its renewable and sustainable nature. Accurate wind speed prediction is essential for the stable functioning of wind turbines to generate wind power. However, the flexible and intermittent nature of wind speed makes accurate wind speed forecasting a challenging task. The proposed wind speed forecasting framework combines the features of various data decomposition techniques and Bidirectional Long Short Term Memory (BiDLSTM) networks. Presently, Data Decomposition models such as the Wavelet Transform are extensively employed for wind speed forecasting to improve the accuracy of the forecasting models. Hence, in this paper, various data decomposition techniques that can denoise the signal are investigated and applied to partition the input time series into several high and low-frequency signals. The data decomposition methods, namely, Wavelet Transform, Empirical Model Decomposition, Ensemble Empirical Mode Decomposition, and Empirical Wavelet Transform, have been applied to denoise the dataset. The low and high-frequency sub-series are forecasted separately using Bidirectional LSTM networks, and the forecasting outcomes of low and high-frequency signals are aggregated to get the final forecasting results. The empirical results establish that the proposed EWT- based hybrid model outperforms other decomposition-based models in accuracy and stability. The performance of the EWT-BiDLSTM model is further compared with Bidirectional LSTM networks with skip connections. The experimental results substantiate that the proposed decompositionbased hybrid deep BiDLSTM models with skip connections exhibit better prediction accuracy than other models.
引用
收藏
页数:26
相关论文
共 51 条
  • [1] An iterative wavelet threshold for signal denoising
    Bayer, Fabio M.
    Kozakevicius, Alice J.
    Cintra, Renato J.
    [J]. SIGNAL PROCESSING, 2019, 162 : 10 - 20
  • [2] Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization
    Chen, Jie
    Zeng, Guo-Qiang
    Zhou, Wuneng
    Du, Wei
    Lu, Kang-Di
    [J]. ENERGY CONVERSION AND MANAGEMENT, 2018, 165 : 681 - 695
  • [3] A novel compound wind speed forecasting model based on the back propagation neural network optimized by bat algorithm
    Cui, Yanbin
    Huang, Chenchen
    Cui, Yanping
    [J]. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2020, 27 (07) : 7353 - 7365
  • [4] A gated recurrent unit neural networks based wind speed error correction model for short-term wind power forecasting
    Ding, Min
    Zhou, Hao
    Xie, Hua
    Wu, Min
    Nakanishi, Yosuke
    Yokoyama, Ryuichi
    [J]. NEUROCOMPUTING, 2019, 365 : 54 - 61
  • [5] Duan XW, 2015, INT CONF CONTR AUTO, P197, DOI 10.1109/ICCAIS.2015.7338661
  • [6] A new ensemble empirical mode decomposition (EEMD) denoising method for seismic signals
    Gaci, Said
    [J]. EUROPEAN GEOSCIENCES UNION GENERAL ASSEMBLY 2016, 2016, 97 : 84 - 91
  • [7] Empirical Wavelet Transform
    Gilles, Jerome
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2013, 61 (16) : 3999 - 4010
  • [8] Graves A, 2012, STUD COMPUT INTELL, V385, P1, DOI [10.1162/neco.1997.9.1.1, 10.1007/978-3-642-24797-2]
  • [9] Gui T, 2019, AAAI CONF ARTIF INTE, P6481
  • [10] Wind power forecast based on improved Long Short Term Memory network
    Han, Li
    Jing, Huitian
    Zhang, Rongchang
    Gao, Zhiyu
    [J]. ENERGY, 2019, 189