Gaussian Mixture Models for the Optimal Sparse Sampling of Offshore Wind Resource

Abstract

Abstract. Offshore wind resource assessment is a crucial step for the development of offshore wind energy. It relies on the installation of measurement devices, which placement is an open challenge for developers. In this paper, a sparse sampling method using a Gaussian Mixture Model on Numerical Weather Prediction data is developed for the offshore wind reconstruction. It is applied on France's main offshore wind energy development areas, Normandy, Southern Brittany, and the Mediterranean Sea. The study is based on 3 years of Meteo France AROME's data, available through the MeteoNet data-set. Using a Gaussian Mixture Model for data clustering, it yields to optimal sensors' locations with regards to wind field reconstruction error. The proposed workflow is described and compared to state-of-the-art methods for sparse sampling. It constitutes a robust yet simple method for the definition of optimal sensor siting for offshore wind reconstruction. The described method yields to optimal network of 7, 4, and 4 sensors for Normandy, Southern Brittany and the Mediterranean Sea with a gain of approximately 20 % in wind field reconstruction error compared to the median Monte Carlo case, and more than 30 % compared to state-of-the-art methods.