Modeling the Variability of Sydney Harbor Wind Measurements

Abstract

The time-dependent behavior in the variability of wind measurements is investigated using bivariate generalized autoregressive conditional heteroscedastic models. These models express the current level of short-timescale wind variability in terms of previous observed values of the fluctuations from mean wind fields. As such, these models provide a useful descriptive model that can be applied to short-term forecasting of variability of wind fluctuations around local mean levels.