Some kinds of nonlinear strengthening operators for predicting the output value of china's marine electric power industry

Abstract

An efficient way to deal with the time series prediction problem in grey perturbed systems is by constructing effective grey operators. Due to the fixed structures of existing strengthening operators, the action intensity of these operators cannot be effectively controlled. This study aims to propose some nonlinear strengthening operators with flexible structures to effectively control the action intensity of operators to raw data and obtain the optimum prediction accuracy. Based on the axiom system of grey operators, the power average strengthening operator (PASO), the geometric power average strengthening operator (GPASO), the weighted power average strengthening operator (WPASO), the weighted geometric power average strengthening operator (WGPASO) are each constructed by introducing variable parameters into the construction of strengthening operators. Moreover, the properties of these operators, the relationship between different variable parameters and the action intensity of these operators are studied. Finally, with the prediction of China's marine electric power industry output value as an example, the effectiveness and superiority of these strengthening operators is confirmed.