公开(公告)号：US20210398048A1

公开(公告)日：2021-12-23

申请号：US17351098

申请日：2021-06-17

Applicant: Shandong University

Inventor： Chenghui ZHANG ,  Che LIU ,  Bo SUN

IPC: G06Q10/06 ,  G06Q10/04 ,  G06Q50/06 ,  G06N20/00 ,  G06N7/08

Abstract: The present disclosure provides a method and system for predicting building energy consumption based on a Holt-Winters and an extreme learning machine, the method including: constructing a building simulation model based on actual operation parameters of a building to obtain an original energy consumption data set of the building; decomposing the original energy consumption data set to obtain a linear energy consumption data set and a nonlinear energy consumption data set; performing prediction on the linear energy consumption data set by using a trained Holt-Winters model to obtain a linear energy consumption prediction result; and inputting the nonlinear energy consumption data set, the original energy consumption data set, and the linear energy consumption prediction result into a trained extreme learning machine model to output a building energy consumption prediction value of the building simulation model.