A novel discrete grey model with time-delayed power term and its application in solar power generation volume forecasting

Abstract

PurposeIn order to accurately forecast nonlinear and complex characteristics of solar power generation in China, a novel discrete grey model with time-delayed power term (abbreviated as is proposed in this paper.Design/methodology/approachFirstly, the time response function is deduced by using mathematical induction, which overcomes the defects of the traditional grey model. Then, the genetic algorithm is employed to determine the optimal nonlinear parameter to improve the flexibility and adaptability of the model. Finally, two real cases of installed solar capacity forecasting are given to verify the proposed model, showing its remarkable superiority over seven existing grey models.FindingsGiven the reliability and superiority of the model, the model is applied to forecast the development trend of China's solar power generation in the coming years. The results show that the proposed model has higher prediction accuracy than the comparison models.Practical implicationsThis paper provides a scientific and efficient method for forecasting solar power generation in China with nonlinear and complex characteristics. The forecast results can provide data support for government departments to formulate solar industry development policies.Originality/valueThe main contribution of this paper is to propose a novel discrete grey model with time-delayed power term, which can handle nonlinear and complex time series more effectively. In addition, the genetic algorithm is employed to search for optimal parameters, which improves the prediction accuracy of the model.