Study of Short-term Power Load Forecasting Based on the VMD-BES-LSSVM Model

To address the challenges of short-term load forecasting, including difficulty and low accuracy, a short-term load forecasting method based on the VMD-BES-LSSVM model is proposed. This method first uses Variational Mode Decomposition(VMD) to decompose load data into individual intrinsic mode functions(IMFs) to reduce data non-stationarity and noise. Then, the Bald Eagle Search(BES) algorithm is employed to optimize the penalty and kernel parameters of the Least Squares Support Vector Machine(LSSVM), improving the model′s generalization ability and prediction accuracy. Finally, the optimized LSSVM model is applied to predict each IMF component, and the prediction results of each subsequence are reconstructed to obtain the final load forecasting result. Simulation results based on real load data from Quanzhou demonstrate that this method can be effectively applied to short-term load forecasting, with accuracy superior to traditional forecasting methods.