Premium
Wind speed modeled as an indexed semi‐Markov process
Author(s) -
D'Amico Guglielmo,
Petroni Filippo,
Prattico Flavio
Publication year - 2013
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.2215
Subject(s) - autocorrelation , wind speed , markov process , computer science , markov chain , markov model , wind power , hidden markov model , statistics , meteorology , mathematics , machine learning , artificial intelligence , engineering , geography , electrical engineering
The production of energy through wind turbines is increasing enormously in the latest years. To better design wind turbines, a good model for wind speed is needed. In a previous paper, we showed that semi‐Markov processes are more appropriate for this purpose than simple Markov processes, but to reach an accurate reproduction of real data features, high order models should be used. In this work, we introduce an indexed semi‐Markov process that is able to reproduce the most important statistical features of wind speed data, namely, the probability density function and the autocorrelation function, without the necessity of higher order models. We downloaded a database, freely available from the Web, of wind speed data taken from Lastem station, Italy and sampled every 10 min. We then generate synthetic time series for wind speed by means of Monte Carlo simulations. The time lagged autocorrelation is then used to compare statistical properties of the proposed model with those of real data and also with a synthetic time series generated though a simple semi‐Markov process. Copyright © 2013 John Wiley & Sons, Ltd.