Regional data center demand potential combination prediction method and device

The invention discloses a regional data center demand potential combined prediction method and device based on a neural network model, and the method comprises the steps: carrying out the analysis and quantification of the influence factors of the demand of a regional data center, obtaining an initial data set, and carrying out the definition and quantification of a data center demand potential value; performing dimensionless processing on the initial data set to obtain a dimensionless data set, and inputting the dimensionless data set into a combined prediction model for model training; performing trend extrapolation on the initial data set to obtain future index data, and inputting the obtained index data into the trained combined prediction model for prediction; and carrying out weight distribution on a prediction result by adopting a covariance weight distribution method to obtain a data center demand potential value. According to the invention, the future index data of the influence factors are respectiv