Adaptive Gaussian Process for Short-Term Wind Speed Forecasting

We study the problem of short term wind speed prediction, which is a critical factor for effective wind power generation. This is a challenging task due to the complex and stochastic behavior of the wind environment. Observing various periods in the wind speed time series present different patterns, we suggest a nonlinear adaptive framework to model various hidden dynamic processes. The model is essentially data driven, which leverages non-parametric Heteroscdastic Gaussian Process to model relevant patterns for short term prediction. We evaluate our model on two different real world wind speed datasets from National Data Buoy Center. We compare our results to state-of-arts algorithms to show improvement in terms of both Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE).

[1]  A. Shamshad,et al.  First and second order Markov chain models for synthetic generation of wind speed time series , 2005 .

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

[3]  Marija D. Ilic,et al.  Model predictive economic/environmental dispatch of power systems with intermittent resources , 2009, 2009 IEEE Power & Energy Society General Meeting.

[4]  Alexander J. Smola,et al.  Heteroscedastic Gaussian process regression , 2005, ICML.

[5]  Guy P. Nason,et al.  Wind Speed Modelling and Short-Term Prediction Using Wavelets , 2001 .

[6]  Wolfram Burgard,et al.  Most likely heteroscedastic Gaussian process regression , 2007, ICML '07.

[7]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[8]  Ömer Nezih Gerek,et al.  Mycielski approach for wind speed prediction , 2009 .

[9]  Matthias W. Seeger,et al.  Gaussian Processes For Machine Learning , 2004, Int. J. Neural Syst..

[10]  J.C. Palomares-Salas,et al.  ARIMA vs. Neural networks for wind speed forecasting , 2009, 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.

[11]  F. Y. Ettoumi,et al.  Statistical bivariate modelling of wind using first-order Markov chain and Weibull distribution , 2003 .

[12]  J. J. G. de la Rosa,et al.  Comparison of Models for Wind Speed Forecasting , 2009 .

[13]  Athanasios Sfetsos,et al.  A comparison of various forecasting techniques applied to mean hourly wind speed time series , 2000 .

[14]  Michael I. Jordan,et al.  Regression with input-dependent noise: A Gaussian process treatment , 1998 .

[15]  Piers R. J. Campbell,et al.  WIND SPEED MODELLING AND SHORT-TERM PREDICTION USING WAVELETS , .