Electric power price prediction method, system, equipment and medium

The invention relates to the technical field of electricity market transaction, in particular to an electricity price prediction method, system and device and a medium. Firstly, collected original power data are preprocessed; secondly, converting the preprocessed original power data into an adjacent matrix topological graph, and performing graph convolution operation on an adjacent matrix to obtain embedded vectors of different dimensions; splicing the embedded vectors of different dimensions and the preprocessed original power data to obtain spliced data, and obtaining a weighted vector according to the spliced data; and finally, obtaining to-be-predicted power transaction price data according to the weighted vector. The method achieves the efficient extraction of multi-dimensional correlation features, deeply extracts the long-term dependency relationship and local time sequence dependency change, guarantees the higher accuracy of price prediction in a complex electricity market environment, and also guaran