Power load curve prediction method and device based on big data, and storage medium

The invention discloses a power load curve prediction method and device based on big data, and a storage medium, and relates to the technical field of power consumption prediction. The method comprises the steps of obtaining user portrait data of a to-be-predicted user, date parameters of a to-be-predicted day and weather forecast parameters; splicing the user portrait data, the date parameter and the weather forecast parameter to obtain a splicing parameter; the splicing parameters are used as input of an electricity consumption prediction model for operation, and predicted electricity consumption data are obtained; acquiring a plurality of historical splicing parameters matched with the splicing parameters from a historical electricity consumption database; based on a plurality of historical power load curves corresponding to the plurality of historical splicing parameters, determining a power load proportion of each time period within one day; and determining a power load curve of the to-be-predicted user