Environmental data processing by clustering methods for energy forecast and planning

This paper presents a statistical approach based on the k-means clustering technique to manage environmental sampled data to evaluate and to forecast of the energy deliverable by different renewable sources in a given site. In particular, wind speed and solar irradiance sampled data are studied in association to the energy capability of a wind generator and a photovoltaic (PV) plant, respectively. The proposed method allows the sub-sets of useful data, describing the energy capability of a site, to be extracted from a set of experimental observations belonging the considered site. The data collection is performed in Sicily, in the south of Italy, as case study. As far as the wind generation is concerned, a suitable generator, matching the wind profile of the studied sites, has been selected for the evaluation of the producible energy. With respect to the photovoltaic generation, the irradiance data have been taken from the acquisition system of an actual installation. It is demonstrated, in both cases, that the use of the k-means clustering method allows data that do not contribute to the produced energy to be grouped into a cluster, moreover it simplifies the problem of the energy assessment since it permits to obtain the desired information on energy capability by managing a reduced amount of experimental samples. In the studied cases, the proposed method permitted a reduction of the 50% of the data with a maximum discrepancy of 10% in energy estimation compared to the classical statistical approach. Therefore, the adopted k-means clustering technique represents an useful tool for an appropriate and less demanding energy forecast and planning in distributed generation systems.