A Machine Learning Approach for Wind Speed Forecasting in Microgrids

Abstract

This paper presents a wind speed forecasting method based on machine learning approach applied to microgrids. A small wind turbine is modeled then the forecasting method is developed to estimate the wind speed and the potential of energy production in a wind farm. The accuracy of this method is higher compared to other existing methods in the literature for time series analysis such as artificial neural networks (ANN). This study is focused on a case study with the real data from weather station of Basel in Switzerland. The results obtained are presented and discussed.