An Improved GM(1,1)-Genetic Algorithm to Short-Term Forcasting in Power System

GM model is widely applied in many fields, in this paper, a refined GM(l,l)-improved genetic algorithm (GM(1,1)- IGA) is put forward to solve short-term load forecasting (STLF) problems in power system. Traditional GM(1,1) forecasting model is not accurate and the value of parameter a is constant, while the proposed algorithm could overcome these disadvantages. GM(1,1)-IGA established a function Z(c) to find the constant number, which enhanced the accuracy of solution, in addition, in order to construct optimal grey model GM(1,1) to enhance the accuracy of forecasting, the improved decimal-code genetic algorithm (GA) is applied to search the optimal a value of grey model GM(1,1). What´s more, this paper also proposes the one-point linearity arithmetical crossover, which can greatly improve the speed of crossover and mutation. Then, a comparison of the performance has been made between GM(1,1)- IGA and traditional GM(1,1) forecasting model. Finally, a daily load forecasting example is used to test the GM(1,1)-IGA model. Results show that the GM(1,1)-IGA had better accuracy and practicality.