Short-term power load prediction method, device and equipment

The embodiment of the invention provides a short-term power load prediction method, device and equipment. The method comprises the following steps: acquiring power demand time sequence data, and decomposing the data into a high-pass coefficient and a low-pass coefficient; respectively carrying out convolution with a wavelet function to obtain wavelet coefficients of different frequency bands, and arranging the wavelet coefficients in sequence to obtain an input feature vector; performing wavelet coefficient optimization on the input feature vector through a differential evolution algorithm to obtain a radial basis function neural network model based on the differential evolution optimization algorithm; performing parameter adjustment on the radial basis function neural network model based on the differential evolution optimization algorithm; and predicting the load at a future time point by using the parameter-adjusted radial basis function neural network model based on the differential evolution optimization