Industrial user load prediction method based on improved empirical Fourier decomposition

The invention discloses an industrial user load prediction method based on improved empirical Fourier decomposition, and the method comprises the steps: obtaining original industrial user load data, and carrying out the preprocessing of the industrial user load data; the method comprises the following steps of: decomposing industrial user load data by adopting an IEFD method, and decomposing data containing impact load into components of different modes and residual components; dividing the obtained load sequence component into a high-frequency component and a low-frequency component by adopting a zero-crossing rate Pzero; establishing an IBES-BiLSTM prediction model to predict the high-frequency component to obtain a prediction result of the high-frequency component, and establishing an IBES-LSSVR prediction model to predict the low-frequency component to obtain a prediction result of the low-frequency component; reconstructing the prediction result of the high-frequency component and the prediction result o