Wind Speed Forecasting Based on FEEMD and LSSVM Optimized by the Bat Algorithm

Affected by various environmental factors, wind speed presents high fluctuation, nonlinear and non-stationary characteristics. To evaluate wind energy properly and efficiently, this paper proposes a modified fast ensemble empirical model decomposition (FEEMD)-bat algorithm (BA)-least support vector machines (LSSVM) (FEEMD-BA-LSSVM) model combined with input selected by deep quantitative analysis. The original wind speed series are first decomposed into a limited number of intrinsic mode functions (IMFs) with one residual series. Then a LSSVM is built to forecast these sub-series. In order to select input from environment variables, Cointegration and Granger causality tests are proposed to check the influence of temperature with different leading lengths. Partial correlation is applied to analyze the inner relationships between the historical speeds thus to select the LSSVM input. The parameters in LSSVM are fine-tuned by BA to ensure the generalization of LSSVM. The forecasting results suggest the hybrid approach outperforms the compared models.

[1]  Li Hui,et al.  One hour ahead prediction of wind speed based on data mining , 2010, 2010 2nd International Conference on Advanced Computer Control.

[2]  Wang Zengping,et al.  Wind Power Prediction Considering Nonlinear Atmospheric Disturbances , 2015 .

[3]  Il-Yop Chung,et al.  An Analysis of Variable-Speed Wind Turbine Power-Control Methods with Fluctuating Wind Speed , 2013 .

[4]  P. N. Suganthan,et al.  A Comparative Study of Empirical Mode Decomposition-Based Short-Term Wind Speed Forecasting Methods , 2015, IEEE Transactions on Sustainable Energy.

[5]  Esmaeil Hadavandi,et al.  A bat-neural network multi-agent system (BNNMAS) for stock price prediction: Case study of DAX stock price , 2015, Appl. Soft Comput..

[6]  Thomas Bak,et al.  Damping Wind and Wave Loads on a Floating Wind Turbine , 2013 .

[7]  Haiyan Lu,et al.  Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model , 2012 .

[8]  Wang Xiaolan,et al.  One-Month Ahead Prediction of Wind Speed and Output Power Based on EMD and LSSVM , 2009, 2009 International Conference on Energy and Environment Technology.

[9]  Wen-Yeau Chang,et al.  SHORT-TERM WIND POWER FORECASTING USING THE ENHANCED PARTICLE SWARM OPTIMIZATION BASED HYBRID METHOD , 2013 .

[10]  Hamidreza Zareipour,et al.  Forecasting aggregated wind power production of multiple wind farms using hybrid wavelet‐PSO‐NNs , 2014 .

[11]  Heping Liu,et al.  Comprehensive evaluation of ARMA–GARCH(-M) approaches for modeling the mean and volatility of wind speed , 2011 .

[12]  Su-Hua Yang,et al.  Novel SrGa2 O 4 Phosphor for Tunable Blue-White Luminescence , 2005 .

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

[14]  Yung-Hung Wang,et al.  On the computational complexity of the empirical mode decomposition algorithm , 2014 .

[15]  Dongxiao Niu,et al.  Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm , 2014 .

[16]  David Wenzhong Gao,et al.  Condition Parameter Modeling for Anomaly Detection in Wind Turbines , 2014 .

[17]  Chang Jun-fu.  Short-term Wind Power Prediction Based on Modified Particle Swarm Optimization Algorithm , 2012 .

[18]  Jianzhou Wang,et al.  Combined forecasting models for wind energy forecasting: A case study in China , 2015 .

[19]  Norden E. Huang,et al.  Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method , 2009, Adv. Data Sci. Adapt. Anal..

[20]  Juan José González de la Rosa,et al.  Exogenous Measurements from Basic Meteorological Stations for Wind Speed Forecasting , 2013 .

[21]  Wang Jilong,et al.  Short-term wind speed forecasting based on spectral clustering and optimised echo state networks , 2015 .

[22]  Qunying Liu,et al.  A short-term wind speed forecasting model based on improved QPSO optimizing LSSVM , 2014, 2014 International Conference on Power System Technology.

[23]  Rongning Wu.  Least absolute deviation estimation for general fractionally integrated autoregressive moving average time series models , 2014 .

[24]  Ray-Yeng Yang,et al.  Potential of Offshore Wind Energy and Extreme Wind Speed Forecasting on the West Coast of Taiwan , 2015 .

[25]  Xin-She Yang,et al.  Nature-Inspired Metaheuristic Algorithms , 2008 .

[26]  Xiao Yang,et al.  WIND SPEED AND GENERATED POWER FORECASTING IN WIND FARM , 2005 .

[27]  Yao Hai-tao.  The short-term wind speed forecast analysis based on the PSO-LSSVM predict model , 2012 .

[28]  Ying-Yi Hong,et al.  Hour-Ahead Wind Speed and Power Forecasting Using Empirical Mode Decomposition , 2013 .

[29]  Qingwu Gong,et al.  Insulator ESDD forecasting under complex climate conditions on the basis of LSSVM , 2009, 2009 IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications.

[30]  Li Jun-jie.  Prediction model based on least squares support vector machine with harmony search and its application , 2009 .

[31]  Douglas A. Smith,et al.  Time series analysis of wind speed using VAR and the generalized impulse response technique , 2007 .

[32]  Myeongsu Kang,et al.  Reliable fault diagnosis for incipient low-speed bearings using fault feature analysis based on a binary bat algorithm , 2015, Inf. Sci..

[33]  Maria Grazia De Giorgi,et al.  Comparison Between Wind Power Prediction Models Based on Wavelet Decomposition with Least-Squares Support Vector Machine (LS-SVM) and Artificial Neural Network (ANN) , 2014 .

[34]  B. Venkateswara Rao,et al.  Optimal power flow by BAT search algorithm for generation reallocation with unified power flow controller , 2015 .

[35]  Wen Jiang,et al.  Wind speed forecasting using autoregressive moving average/generalized autoregressive conditional heteroscedasticity model , 2012 .

[36]  Chandrasekhar Yammani,et al.  Optimal placement and sizing of multi Distributed generations with renewable bus available limits using Shuffled Bat algorithm , 2014, 2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE).