Markov Chain Modelling for Very-Short-term Wind Power Forecasting

A Wind power forecasting method based on the use of discrete time Markov chain models is developedstarting from real wind power time series data. It allows to directly obtain in an easy way an estimateof the wind power distributions on a very short-term horizon, without requiring restrictive assumptionson wind power probability distribution. First and Second Order Markov Chain Model are analyticallydescribed. Finally, the application of the proposed method is illustrated with reference to a set of realdata.