Clustering Daily Wind Speed Time Series

Abstract

This chapter deals with the problem of clustering daily wind speed time series based on two features referred to as $W_r$ and H, representing a measure of the relative average wind speed and the Hurst exponent, respectively. It is shown that using these features daily, wind speed patterns can be clustered into 2 or 3 classes and some useful statistical properties, such as the class weight and the persistence of patterns in a class, can be estimated.