Research on probability density modeling method of wind power fluctuation based on nonparametric kernel density estimation

Abstract

Since the research on probability density distribution model of wind power fluctuation is of great importance for wind power integration and operation, this paper proposes a novel modeling method for the wind power fluctuation probability density based on nonparametric kernel density estimation. Firstly, the fluctuation components of wind power are extracted by wavelet decomposition to build a model involved bandwidth optimization, which is based on nonparametric kernel density estimation. Then a bandwidth optimization model is built constrained by goodness of fit test. Finally, constrained ordinal optimization is adopted to solve the model. Simulation results show that the model constructed by nonparametric kernel density estimation is determined by sample data without a prior probability density distribution, therefore this modelling method features with higher accuracy and more general applicability. In addition, an improved strategy proposed in this paper for nonparametric kernel density estimation also greatly improves the modeling accuracy and computational efficiency.