Wind Power Prediction Based on a Hybrid Granular Chaotic Time Series Model

Abstract

For realizing high-accuracy short-term wind power prediction, a hybrid model considering physical features of data is proposed in this paper, with consideration of chaotic analysis and granular computing. First, considering the chaotic features of wind power time series physically, data reconstruction in chaotic phase space is studied to provide a low-dimensional input with more information in modeling. Second, considering that meteorological scenarios of wind development are various, complicated, and uncertain, typical chaotic time series prediction models and wind scenarios are analyzed correspondingly via granular computing (GrC). Finally, through granular rule-based modeling, a hybrid model combining reconstructed wind power data and different models is constructed for short-term wind power prediction. Data from real wind farms is taken for experiments, validating the feasibility and effectiveness of the proposed wind power prediction model.