Self-adaptive discrete grey model based on a novel fractional order reverse accumulation sequence and its application in forecasting clean energy power generation in China

With the increasing power consumption in China and the urgent demand for environmental protection, promoting the development of clean energy power generation industry is the only way to optimize the energy power generation structure. It is very important to effectively predict the development trend of China's clean energy power generation system with complex, changeable and limited data. To address this issue, this paper defines a novel fractional self-adaptive reverse accumulation sequence, and combines discrete modeling techniques and time power terms to propose a novel fractional self-adaptive reverse accumulation with time power terms. The parameter estimation and time response formula of the new model are derived. The matrix perturbation theory is used to prove that the new model satisfies the new information priority principle. The Grey Wolf Optimizer is used to optimize the self-adaptive parameter r and non-negative constant a. Finally, the prediction model is constructed for the power generation capacity of five representative types of clean energy in China: biomass, wind, nuclear, natural gas and hydro power, the prediction result shows that the new model has higher prediction accuracy and data applicability than the other five grey models. According to these prediction results, relevant suggestions on the development of China's clean energy are provided to decision makers. (C) 2022 Elsevier Ltd. All rights reserved.

Automated summary

This paper investigates the issue of predicting the development trend of China's clean energy power generation system. It proposes a new prediction model by defining a novel fractional self-adaptive reverse accumulation sequence and combining discrete modeling techniques and time power terms. The Grey Wolf Optimizer is used for parameter optimization. The prediction results show that the model has higher accuracy and applicability, providing relevant suggestions to decision makers.