Abstract: Based on the analysis of inherent errors in traditional GM(1,1) power model,this paper puts forward Unbiased GM(1,1) power model.It is theoretically proved that the complete coincidence of the prediction and simulation to the original data of its time response curve generated form has achieved.The unbiased model presented in this paper has completely eliminated the inherent simulant error of the traditional model,but also avoided the jumping errors from the differential equation to differential equation in traditional grey modeling.The application of this model covers unbiased GM(1,1) model and gray discrete model.Numerical simulation and case analysis shows that the simulation and prediction accuracy in traditional modeling has been significantlg improved by unbiased GM(1,1) power model.

Key words: grey system, unbiased GM(1, 1) power model, parameters optimization, forecasting, forecasting