Hybrid Forecasting Model for Very-Short Term Wind Power Forecasting Based on Grey Relational Analysis and Wind Speed Distribution Features

Abstract

Very-short term wind power forecasting is one of the most effective ways to deal with the challenges of increased penetration of wind power into the electric grid due to its fluctuation and volatility. To improve wind power forecasting by taking advantage of each independent forecasting model, a hybrid model is proposed by means of grey relational analysis and wind speed distribution features. The weight of each independent model is estimated according to different wind speed subsection and similar wind speed frequency. The case study shows that the hybrid forecasting model has broader applications in very-short term (15-minute-ahead) wind power output forecasting.