Improved genetic algorithm-GM(1,1) for power load forecasting problem

According to Traditional GM(1, 1) forecasting model is not accurate and the value of parameter a is constant, in order to overcome these disadvantages, this paper put forward an improved genetic algorithm-GM(l, 1) (IGA-GM (1, 1)) to solve the problem of short-term load forecasting (STLF) in power system. The proposed algorithm construct optimal grey model GM(1, 1) to enhance the accuracy of forecasting, and 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 in genetic algorithm, which can greatly improve the speed of crossover and mutation. At last, this proposed algorithm improved the residual error test which lead to the results more accurate, and a comparison of the performance has been made between IGA-GM(1, 1) and traditional GM(1, 1) forecasting model. Results show that the IGA-GM(1, 1) had better accuracy and practicality.