Method for processing irradiation forecast, method for training stacked generalization model, and apparatuses thereof

Abstract

Disclosed is a method for processing an irradiation forecast. The method includes: acquiring irradiation forecast data corresponding to a target time period; calling a stacked generalization model including a first-layer generalizer and a second-layer generalizer; determining, using the first-layer generalizer, intermediate forecast data based on the irradiation forecast data corresponding to the target time period; and determining, using the second-layer generalizer, an output forecast value corresponding to the target time period based on the intermediate forecast data. In a technical solution according to an embodiment of the present disclosure, a method for processing an irradiation forecast is achieved. In addition, in a technical solution according to the embodiment of the present disclosure, intermediate forecast data outputted by the first-level generalizer acts as an input of the second-level generalizer, such that a deviation of an output result of the first-layer generalizer is reduced by the second-layer generalizer, thereby reducing processing overhead of a server while further improving the accuracy of plane of array irradiation.