Short-term wind power generation point and interval prediction based on a novel seasonal multivariable grey model

Abstract

Developing wind farms is a promising approach to reduce pollution emissions in the electrical power system. Wind power generation prediction plays a key role in emission reduction and energy conservation of wind farms. Considering the distribution information and seasonal meteorological characteristics in wind power generation system, this paper proposes a novel seasonal multivariable grey model. This novel model is proven to provide unbiased prediction on short-term wind power generation. Based on this model, the interval prediction is designed using an intelligent optimization algorithm and the Bootstrap method. For illustration and verification purposes, Belgian onshore and offshore wind farm generation sets are studied. Empirical results indicate that the proposed model achieves higher accuracy compared with six existing models, yielding the lowest MAPE of 1.74% and 1.76% in point prediction, and the best performance of coverage width-based criterion and average interval score in interval prediction.