Computer Vision-Driven Building Energy Modeling Framework for Post-Occupant Interior Energy Consumption
Journal
Construction Research Congress 2022: Computer Applications, Automation, and Data Analytics - Selected Papers from Construction Research Congress 2022
Journal Volume
2-B
Pages
1058-1066
Date Issued
2022
Author(s)
Abstract
As the cities keep expanding and the population continues growing, an immense need to improve the existing buildings' energy performance has emerged in the energy-intensive built environment. One of the critical challenges to improving buildings' energy efficiency is to accurately model and portray the buildings' energy performance. Current research mainly focuses on simulation- and data-driven-based methods to help predict the buildings' energy consumption. However, without information from the buildings' actual use, both methods rely on assumptions and simulated parameters to predict the results. This research developed a computer vision-driven building energy modeling framework that models the power consumption of equipment and home appliances by semantic segmentation of the reality model. The framework is a simulation-based method with interior model based on actual use condition using computer vision-driven method. The framework can improve the simulation result and analyze the energy-consuming source in an existing building. © 2022 ASCE.
Other Subjects
Buildings; Domestic appliances; Energy efficiency; Energy utilization; Semantic Segmentation; Semantics; 'current; Actual use; Building energy efficiency; Building energy model; Building energy performance; Built environment; Critical challenges; Energy; Energy-consumption; Modelling framework; Computer vision
Type
conference paper