A hybrid neural network model for short-term wind speed forecasting based on decomposition, multi-learner ensemble, and adaptive multiple error corrections

Abstract Under the dual stimulus of the new energy demand and the increasing competitiveness of wind energy, the construction of wind speed prediction models began to be placed in a position that cannot be ignored. To overcome the challenges brought by wind speed fluctuations to wind speed forecasting, this paper proposes a novel hybrid wind speed forecasting deep model. The model has three modules, including data preprocessing, multi-learner ensemble, and adaptive multiple error correction. We used four real wind series in Xinjiang, China to verify the performance of the model. The results of the case study show that: (a) The proposed hybrid deep model for wind speed forecasting is superior to several state-of-the-art models in terms of both forecasting stability and forecasting accuracy; (b) The proposed hybrid deep model is excellent in multi-step forecasting, taking the site #1 as an example, the MAEs of the proposed model are 0.0250 m/s, 0.0417 m/s, and 0.0570 m/s, respectively.

[1]  Guoqing Huang,et al.  A novel wind speed prediction method: Hybrid of correlation-aided DWT, LSSVM and GARCH , 2018 .

[2]  Yi-Ming Wei,et al.  An adaptive hybrid model for short term wind speed forecasting , 2020 .

[3]  Ping-Yuan Lu,et al.  The application of neural network in wind speed forecasting , 2015, 2015 IEEE 12th International Conference on Networking, Sensing and Control.

[4]  Jörg K. Wegner,et al.  Scaling machine learning for target prediction in drug discovery using Apache Spark , 2017, Future Gener. Comput. Syst..

[5]  Hossein Hassani,et al.  Selecting optimal lag order in Ljung–Box test , 2020 .

[6]  Lifang Zhang,et al.  A combined forecasting model for time series: Application to short-term wind speed forecasting , 2020 .

[7]  Chrysoula Dimitriou-Fakalou,et al.  The auto-regression and the moving-average , 2010 .

[8]  Kai Zhang,et al.  A composite framework coupling multiple feature selection, compound prediction models and novel hybrid swarm optimizer-based synchronization optimization strategy for multi-step ahead short-term wind speed forecasting , 2020 .

[9]  Kai Wang,et al.  Multi-step short-term wind speed forecasting approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA optimization and ELM , 2019, Energy Conversion and Management.

[10]  Qinghua Hu,et al.  Robust functional regression for wind speed forecasting based on Sparse Bayesian learning , 2019, Renewable Energy.

[11]  Jianzhou Wang,et al.  A hybrid approach based on the Gaussian process with t-observation model for short-term wind speed forecasts , 2017 .

[12]  Rui Yang,et al.  Wind speed forecasting using a new multi-factor fusion and multi-resolution ensemble model with real-time decomposition and adaptive error correction , 2020 .

[13]  Minxia Luo,et al.  Outlier-robust extreme learning machine for regression problems , 2015, Neurocomputing.

[14]  Fulei Chu,et al.  Non-parametric hybrid models for wind speed forecasting , 2017 .

[15]  Qinghua Hu,et al.  Noise model based v-support vector regression with its application to short-term wind speed forecasting , 2014, Neural Networks.

[16]  Hui Liu,et al.  A vanishing moment ensemble model for wind speed multi-step prediction with multi-objective base model selection , 2020 .

[17]  Sebastian Lerch,et al.  Combining predictive distributions for the statistical post-processing of ensemble forecasts , 2016, International Journal of Forecasting.

[18]  Hui Liu,et al.  Smart wind speed deep learning based multi-step forecasting model using singular spectrum analysis, convolutional Gated Recurrent Unit network and Support Vector Regression , 2019 .

[19]  Hui Liu,et al.  Wind speed prediction model using singular spectrum analysis, empirical mode decomposition and convolutional support vector machine , 2019, Energy Conversion and Management.

[20]  Thoranin Sujjaviriyasup,et al.  A new class of MODWT-SVM-DE hybrid model emphasizing on simplification structure in data pre-processing: A case study of annual electricity consumptions , 2017, Appl. Soft Comput..

[21]  Ramchandra Manthalkar,et al.  Time series decomposition and predictive analytics using MapReduce framework , 2019, Expert Syst. Appl..

[22]  S. N. Deepa,et al.  Optimized nonlinear neural network architectural models for multistep wind speed forecasting , 2019, Comput. Electr. Eng..

[23]  Kamran Iqbal,et al.  Surface myoelectric signal classification using the AR-GARCH model , 2014, Biomed. Signal Process. Control..

[24]  Hui Liu,et al.  A novel ensemble model of different mother wavelets for wind speed multi-step forecasting , 2018, Applied Energy.

[25]  Hui Liu,et al.  Corrected multi-resolution ensemble model for wind power forecasting with real-time decomposition and Bivariate Kernel density estimation , 2020 .

[26]  Hui Liu,et al.  Smart wind speed forecasting approach using various boosting algorithms, big multi-step forecasting strategy , 2019, Renewable Energy.

[27]  Jun Liang,et al.  Short-term wind power combined forecasting based on error forecast correction , 2016 .

[28]  Jian Wang,et al.  A hybrid forecasting approach applied in wind speed forecasting based on a data processing strategy and an optimized artificial intelligence algorithm , 2018, Energy.

[29]  P. Drobinski,et al.  Sub-hourly forecasting of wind speed and wind energy , 2020 .

[30]  José Manuel Benítez,et al.  On the use of cross-validation for time series predictor evaluation , 2012, Inf. Sci..

[31]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[32]  Chengshi Tian,et al.  A novel two-stage forecasting model based on error factor and ensemble method for multi-step wind power forecasting , 2019, Applied Energy.

[33]  Yan Jiang,et al.  Short-term wind speed prediction: Hybrid of ensemble empirical mode decomposition, feature selection and error correction , 2017 .

[34]  Yitao Liu,et al.  Deep belief network based deterministic and probabilistic wind speed forecasting approach , 2016 .

[35]  Alban Kuriqi,et al.  Optimisation of cascade reservoir operation considering environmental flows for different environmental management classes , 2020 .

[36]  Yanfei Li,et al.  Smart multi-step deep learning model for wind speed forecasting based on variational mode decomposition, singular spectrum analysis, LSTM network and ELM , 2018 .

[37]  L. Garrote,et al.  Flow regime aspects in determining environmental flows and maximising energy production at run-of-river hydropower plants , 2019 .

[38]  Zishu Cheng,et al.  A new combined model based on multi-objective salp swarm optimization for wind speed forecasting , 2020, Appl. Soft Comput..

[39]  Jujie Wang,et al.  Multi-step ahead wind speed prediction based on optimal feature extraction, long short term memory neural network and error correction strategy , 2018, Applied Energy.

[40]  Yong Bao.  A general result on the estimation bias of ARMA models , 2018, Journal of Statistical Planning and Inference.

[41]  Ying Deng,et al.  A hybrid model based on data preprocessing strategy and error correction system for wind speed forecasting , 2020 .

[42]  Chu Zhang,et al.  A compound structure of ELM based on feature selection and parameter optimization using hybrid backtracking search algorithm for wind speed forecasting , 2017 .

[43]  Jing Zhao,et al.  Multi-step wind speed forecasting based on numerical simulations and an optimized stochastic ensemble method , 2019 .

[44]  Dejie Yu,et al.  A gear fault diagnosis using Hilbert spectrum based on MODWPT and a comparison with EMD approach , 2009 .

[45]  Hui Liu,et al.  A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting , 2020 .

[46]  Yanfei Li,et al.  Big multi-step wind speed forecasting model based on secondary decomposition, ensemble method and error correction algorithm , 2018 .

[47]  Jing Yan,et al.  Advanced wind power prediction based on data-driven error correction , 2019, Energy Conversion and Management.

[48]  António N. Pinheiro,et al.  Water-energy-ecosystem nexus: Balancing competing interests at a run-of-river hydropower plant coupling a hydrologic–ecohydraulic approach , 2020 .

[49]  Hui Liu,et al.  A review on multi-objective optimization framework in wind energy forecasting techniques and applications , 2020 .

[50]  Yu Jin,et al.  A generalized dynamic fuzzy neural network based on singular spectrum analysis optimized by brain storm optimization for short-term wind speed forecasting , 2017, Appl. Soft Comput..

[51]  Luca Delle Monache,et al.  Post-processing techniques and principal component analysis for regional wind power and solar irradiance forecasting , 2016 .

[52]  Amir Mosavi,et al.  Wind speed prediction using a hybrid model of the multi-layer perceptron and whale optimization algorithm , 2020 .

[53]  Hamidreza Zareipour,et al.  A review and discussion of decomposition-based hybrid models for wind energy forecasting applications , 2019, Applied Energy.