has far-reaching sig-nificance for future development of power grid.A short-term load forecasting model based on variational mode decomposition(VMD)and deep belief networks(DBN) is proposed.Firstly
VMD algorithm is used to decompose load data into different intrinsic mode functions(IMF).Secondly
predict each IMF with the help of DBN network.Finally
superimpose the prediction results of each part to obtain prediction results of VMD-DBN model.The experimental results show that compared with simply used DBN method and empirical mode decomposition(EMD)-DBN method
the proposed VMD-DBN method has a significant improvement in prediction precision.