Potential analysis of the transfer learning model in short and medium-term forecasting of building HVAC energy consumption

•Comparing and analyzing the influence of training data on forecasting results.•Proposing a new forecasting method based on load simulation and transfer learning.•Improving the accuracy of load forecasting with only a small amount of historical data.•Discussing the influence of data selection on the...

Full description

Saved in:
Bibliographic Details
Published in:Energy (Oxford) Vol. 193; p. 116724
Main Authors: Qian, Fanyue, Gao, Weijun, Yang, Yongwen, Yu, Dan
Format: Journal Article
Language:English
Published: Oxford Elsevier Ltd 15-02-2020
Elsevier BV
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Comparing and analyzing the influence of training data on forecasting results.•Proposing a new forecasting method based on load simulation and transfer learning.•Improving the accuracy of load forecasting with only a small amount of historical data.•Discussing the influence of data selection on the transfer learning algorithm.
ISSN:0360-5442
1873-6785
DOI:10.1016/j.energy.2019.116724