Diverse dynamical characteristics across the frequency spectrum of wind speed fluctuations

Wind speed oscillations are known to exhibit varying characteristics at different time scales. Our recent analysis has shown that a collection of autoregressive models fitted separately on the frequency components of wind speed data can significantly increase the prediction accuracy. In this paper, we report the results of the investigation of dynamical behaviour across a broad frequency spectrum of wind speed measurements. The results show the existence of diverse characteristics such as stochastic, deterministic and chaotic behaviour apart from the variation of the dimensionality of underlying dynamics as well as the degree of fluctuations. It is also demonstrated that a cluster of deterministic models built upon separate frequency components of a wind speed time series can enhance the prediction accuracy by as much as 80%, on the average, consistently for predictions up to 12 h. The comparison shows the definite advantage of deterministic prediction models over autoregressive models. The f-index introduced in this paper to measure the fluctuations of wind speed over a period indicates that the observed seasonal variations of prediction errors can be correlated with changes in the f-index of the component series contributed mostly by the lower scales of decomposition.

[1]  T. O. Halawani,et al.  A neural networks approach for wind speed prediction , 1998 .

[2]  Mohammad Monfared,et al.  A new strategy for wind speed forecasting using artificial intelligent methods , 2009 .

[3]  R. Kavasseri,et al.  Day-ahead wind speed forecasting using f-ARIMA models , 2009 .

[4]  K. Satheesh Kumar,et al.  Deterministic nature of the underlying dynamics of surface wind fluctuations , 2012 .

[5]  Maria Grazia De Giorgi,et al.  Error analysis of short term wind power prediction models , 2011 .

[6]  M. Negnevitsky,et al.  Very short-term wind forecasting for Tasmanian power generation , 2006, 2006 IEEE Power Engineering Society General Meeting.

[7]  Pak Wai Chan,et al.  Investigation of offshore wind energy potential in Hong Kong based on Weibull distribution function , 2015 .

[8]  G. V. Drisya,et al.  Deterministic prediction of surface wind speed variations , 2014 .

[9]  Xiaolan Wang,et al.  Multiscale prediction of wind speed and output power for the wind farm , 2012 .

[10]  Holger Kantz,et al.  Practical implementation of nonlinear time series methods: The TISEAN package. , 1998, Chaos.

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

[12]  K. Satheesh Kumar,et al.  Improved week-ahead predictions of wind speed using simple linear models with wavelet decomposition , 2016 .

[13]  M. Genton,et al.  Powering Up With Space-Time Wind Forecasting , 2010 .

[14]  P. Grassberger,et al.  Measuring the Strangeness of Strange Attractors , 1983 .

[15]  Hui Liu,et al.  Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction , 2012 .

[16]  Schreiber,et al.  Improved Surrogate Data for Nonlinearity Tests. , 1996, Physical review letters.

[17]  Andrew Kusiak,et al.  Very short-term wind speed forecasting with Bayesian structural break model , 2013 .

[18]  Joseph P. Hennessey.  Some Aspects of Wind Power Statistics , 1977 .

[19]  Athanasios Sfetsos,et al.  A novel approach for the forecasting of mean hourly wind speed time series , 2002 .

[20]  Mohan Kolhe,et al.  Generalized feed-forward based method for wind energy prediction , 2013 .

[21]  James P. Crutchfield,et al.  Geometry from a Time Series , 1980 .

[22]  Fedor Mitschke,et al.  CHAOS VERSUS NOISE IN EXPERIMENTAL DATA , 1993 .

[23]  Henrik Madsen,et al.  A new reference for wind power forecasting , 1998 .

[24]  Kameshwar Poolla,et al.  Exploiting sparsity of interconnections in spatio-temporal wind speed forecasting using Wavelet Transform , 2016 .

[25]  E. Ott.  Chaos in Dynamical Systems: Contents , 1993 .

[26]  Hui Liu,et al.  Forecasting models for wind speed using wavelet, wavelet packet, time series and Artificial Neural Networks , 2013 .

[27]  Michael Negnevitsky,et al.  Wind speed forecast model for wind farm based on a hybrid machine learning algorithm , 2015 .

[28]  A. Celik.  A statistical analysis of wind power density based on the Weibull and Rayleigh models at the southern region of Turkey , 2004 .

[29]  Meenu Gupta,et al.  Wind Power Forecasting: A Review of Statistical Models-Wind Power Forecasting , 2013 .

[30]  O. Makarynskyy,et al.  Chaos and reproduction in sea level , 2013 .

[31]  M. Bilgili,et al.  Application of artificial neural networks for the wind speed prediction of target station using reference stations data , 2007 .

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

[33]  H. Kantz.  A robust method to estimate the maximal Lyapunov exponent of a time series , 1994 .

[34]  Hui Liu,et al.  Wind speed forecasting approach using secondary decomposition algorithm and Elman neural networks , 2015 .

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