Informer-based frequency spectrum prediction model and method

The invention relates to an Informer-based spectrum prediction model and method. The model comprises a high-dynamic system spectrum time sequence processing module, an Informer model and a frequency domain attention calculation module which are connected with one another, the method comprises the following steps: entering a high-dynamic system frequency spectrum time sequence processing module, normalizing an original sequence to obtain a corresponding mean value, a standard deviation and a transformed sequence, embedding the normalized sequence to obtain and send the normalized sequence into an encoder, calculating to obtain an original feature map P, calculating frequency domain attention by using DCT to obtain an enhanced vector r, and performing frequency domain time sequence processing on the enhanced vector r; the method comprises the following steps of: acquiring an original feature map P, splicing the original feature map P with the original feature map P in a frequency dimension to obtain a feature m