Research On Short-Term Load Forecasting Method Based On Rough Set And Gray System Model

Short-term load forecasting methods which take rough set, neural network, grey model as the major content are researched in this paper. Short-term load forecasting method of genetic algorithm neural network based on rough set is proposed, attribute algorithm of rough set theory is introduced to choose neural network's input parameters. Parameters with a high correlation are used for input, which reduce the work and calculation time. In order to solve the shortcoming in the BP algorithm, such as slowness in training speed and convergence to the local minimum, genetic algorithm with the ability of strong global search is integrated. Then a new load Forecasting method of relative factors sensitive mode based on grey system is proposed, to aim to the shortcoming of GM(1,1) bad precision when electric load increases by unexponential function and the weather changes suddenly, a new short-term load forecasting strategy is proposed, which considers relative factors such as temperature, day weather type and so on. Forecasting results of calculation examples show that the two algorithms improve the accuracy of prediction, which are feasible and effective in the short-term load forecasting.