A novel combined model based on echo state network for multi-step ahead wind speed forecasting: A case study of NREL

Abstract Accurate wind speed forecasting plays a crucial role in wind power plants and wind systems. Numerous studies that dedicated to enhance wind speed forecasting accuracy have been proposed. Nevertheless, some classical models are not good at dealing with nonlinear time sequence, and artificial intelligence are easy fall into local optimum. Based on this, this paper proposed a novel combined model for wind speed forecasting, which combined hybrid models based on decomposition method and optimization algorithm. In this approach, four distinct hybrid models are proposed and to additionally enhance the forecasting performance, ESN (Echo state network) is initially applied to integrate all the results obtained by each hybrid model and achieve the ultimate forecasting results. Besides, a distinct data set division mechanism is adopted in the multi-step wind speed forecasting. To verify the effectiveness and versatility of the proposed combined model, the wind speed data of 20 m, 50 m, 80 m per minute of the M2 tower from the National Wind Power Technology Center, United States, are utilized as case studies. The experimental results indicate that the proposed combined model performs better than other conventional methods.

[1]  Jianzhou Wang,et al.  Application of residual modification approach in seasonal ARIMA for electricity demand forecasting: A case study of China , 2012 .

[2]  Haifeng Wang,et al.  Comparison of SVM and LS-SVM for Regression , 2005, 2005 International Conference on Neural Networks and Brain.

[3]  Leandro dos Santos Coelho,et al.  Least squares support vector machines with tuning based on chaotic differential evolution approach applied to the identification of a thermal process , 2012, Expert Syst. Appl..

[4]  Daren Yu,et al.  One-day-ahead probabilistic wind speed forecast based on optimized numerical weather prediction data , 2018 .

[5]  Yanbin Yuan,et al.  Wind power prediction using hybrid autoregressive fractionally integrated moving average and least square support vector machine , 2017 .

[6]  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 .

[7]  Xu Fan,et al.  A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting , 2017 .

[8]  Jianzhou Wang,et al.  Multi-step ahead forecasting in electrical power system using a hybrid forecasting system , 2018, Renewable Energy.

[9]  R. Saidur,et al.  Application of support vector machine models for forecasting solar and wind energy resources: A review , 2018, Journal of Cleaner Production.

[10]  Sinvaldo Rodrigues Moreno,et al.  Wind speed forecasting approach based on Singular Spectrum Analysis and Adaptive Neuro Fuzzy Inference System , 2017, Renewable Energy.

[11]  Yi-Ming Wei,et al.  One day ahead wind speed forecasting: A resampling-based approach , 2016 .

[12]  Liang Chen,et al.  A nonlinear hybrid wind speed forecasting model using LSTM network, hysteretic ELM and Differential Evolution algorithm , 2018, Energy Conversion and Management.

[13]  Hisao Ishibuchi,et al.  Parallel Distributed Hybrid Fuzzy GBML Models With Rule Set Migration and Training Data Rotation , 2013, IEEE Transactions on Fuzzy Systems.

[14]  Ching-Hsue Cheng,et al.  A novel time-series model based on empirical mode decomposition for forecasting TAIEX , 2014 .

[15]  Wenyu Zhang,et al.  A novel hybrid approach for wind speed prediction , 2014, Inf. Sci..

[16]  Kiyoumars Roushangar,et al.  Predicting characteristics of dune bedforms using PSO-LSSVM , 2017 .

[17]  Li Chen,et al.  Sparse algorithm for robust LSSVM in primal space , 2017, Neurocomputing.

[18]  Hisao Ishibuchi,et al.  Parallel Distributed Implementation of Genetics-Based Machine Learning for Fuzzy Classifier Design , 2010, SEAL.

[19]  Chin-Teng Lin,et al.  Multiagent-consensus-MapReduce-based attribute reduction using co-evolutionary quantum PSO for big data applications , 2018, Neurocomputing.

[20]  Huei-Lin Chang,et al.  Hour-ahead wind power and speed forecasting using simultaneous perturbation stochastic approximation (SPSA) algorithm and neural network with fuzzy inputs , 2010 .

[21]  Bo Li,et al.  Multi-scale quantum harmonic oscillator algorithm for global numerical optimization , 2018, Appl. Soft Comput..

[22]  Anatoly A. Zhigljavsky,et al.  Singular Spectrum Analysis for Time Series , 2013, International Encyclopedia of Statistical Science.

[23]  Jiuping Xu,et al.  ROI-based study on impact factors of distributed PV projects by LSSVM-PSO , 2017 .

[24]  Ranjeeta Bisoi,et al.  Prediction interval forecasting of wind speed and wind power using modes decomposition based low rank multi-kernel ridge regression , 2018, Renewable Energy.

[25]  Ganesh K. Venayagamoorthy,et al.  Quantum inspired PSO for the optimization of simultaneous recurrent neural networks as MIMO learning systems , 2010, Neural Networks.

[26]  M. Lange,et al.  Physical Approach to Short-Term Wind Power Prediction , 2005 .

[27]  S. Pandian,et al.  Fuzzy approach for short term load forecasting , 2006 .

[28]  Wei Sun,et al.  Wind speed forecasting using FEEMD echo state networks with RELM in Hebei, China , 2016 .

[29]  Chu Zhang,et al.  A hybrid model based on synchronous optimisation for multi-step short-term wind speed forecasting , 2018 .

[30]  Shan Liu,et al.  An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm , 2016, Expert Syst. Appl..

[31]  Yi Yang,et al.  Modelling a combined method based on ANFIS and neural network improved by DE algorithm: A case study for short-term electricity demand forecasting , 2016, Appl. Soft Comput..

[32]  Chuanjin Yu,et al.  Comparative study on three new hybrid models using Elman Neural Network and Empirical Mode Decomposition based technologies improved by Singular Spectrum Analysis for hour-ahead wind speed forecasting , 2017 .

[33]  Leandro dos Santos Coelho,et al.  Particle swarm approach based on quantum mechanics and harmonic oscillator potential well for economic load dispatch with valve-point effects , 2008 .

[34]  Jianzhou Wang,et al.  A hybrid technique for short-term wind speed prediction , 2015 .

[35]  Yanfei Li,et al.  An experimental investigation of three new hybrid wind speed forecasting models using multi-decomposing strategy and ELM algorithm , 2018 .

[36]  P Arulmozhivarman,et al.  Dynamic Neural Network Based Very Short-Term Wind Speed Forecasting , 2014 .

[37]  Guilherme De A. Barreto,et al.  A New Look at Nonlinear Time Series Prediction with NARX Recurrent Neural Network , 2006, 2006 Ninth Brazilian Symposium on Neural Networks (SBRN'06).

[38]  Adel M. Alimi,et al.  PSO-based analysis of Echo State Network parameters for time series forecasting , 2017, Appl. Soft Comput..

[39]  Jianzhou Wang,et al.  Medium-term wind speeds forecasting utilizing hybrid models for three different sites in Xinjiang, China , 2015 .

[40]  Xiaojun Wu,et al.  Quantum-behaved particle swarm optimization with Gaussian distributed local attractor point , 2011, Appl. Math. Comput..

[41]  Jianzhou Wang,et al.  Research and application of a novel hybrid forecasting system based on multi-objective optimization for wind speed forecasting , 2017 .

[42]  Zhang Yan,et al.  A review on the forecasting of wind speed and generated power , 2009 .

[43]  Leandro dos Santos Coelho,et al.  A chaotic quantum-behaved particle swarm approach applied to optimization of heat exchangers , 2012 .

[44]  N. Ramesh Babu,et al.  Fault classification in power systems using EMD and SVM , 2017 .

[45]  Jianzhou Wang,et al.  The study and application of a novel hybrid forecasting model – A case study of wind speed forecasting in China , 2015 .

[46]  Jian Su,et al.  A novel bidirectional mechanism based on time series model for wind power forecasting , 2016 .

[47]  N. Bigdeli,et al.  Data analysis and short term load forecasting in Iran electricity market using singular spectral analysis (SSA) , 2011 .

[48]  Ioannis B. Theocharis,et al.  A locally recurrent fuzzy neural network with application to the wind speed prediction using spatial correlation , 2007, Neurocomputing.

[49]  Paras Mandal,et al.  A review of wind power and wind speed forecasting methods with different time horizons , 2010, North American Power Symposium 2010.

[50]  Gang Liu,et al.  Quantum-behaved particle swarm optimization for far-distance rapid cooperative rendezvous between two spacecraft , 2018, Advances in Space Research.

[51]  Sun-Yuan Kung,et al.  A delay damage model selection algorithm for NARX neural networks , 1997, IEEE Trans. Signal Process..

[52]  Chuanjin Yu,et al.  An improved Wavelet Transform using Singular Spectrum Analysis for wind speed forecasting based on Elman Neural Network , 2017 .

[53]  Wang Jun,et al.  A new weighted CEEMDAN-based prediction model: An experimental investigation of decomposition and non-decomposition approaches , 2018, Knowl. Based Syst..

[54]  Ergin Erdem,et al.  ARMA based approaches for forecasting the tuple of wind speed and direction , 2011 .

[55]  Wolf-Gerrit Fruh,et al.  Wind forecasting using Principal Component Analysis , 2014 .

[56]  Akin Tascikaraoglu,et al.  A review of combined approaches for prediction of short-term wind speed and power , 2014 .