摘要
A significant part of the world's energy consumption is related to the building sector. Consequently, the execution of improving buildings' energy performance actions is a primary approach to reduce energy dissipation. Building simulation-based optimization is a popular tool for this task; however, it requires the direct coupling of a simulation model with an optimization algorithm that involves intensive and laborious computation. This study aims to reduce computational costs by proposing an optimization procedure based on combining surrogate models with a multi-objective evolutionary algorithm to optimize the building's energy consumption and its occupants' thermal comfort simultaneously. The case study of an existing office building in Kermanshah, Iran was selected to implement and evaluate this suggested optimization strategy. In this study, the input variables are chosen so that, for the studied building, they could be changed without difficulty and high costs. EnergyPlus simulates the situations set by design-of-experiments. The best subsets regression method identifies the regression models which could fit the simulation results with as few factors as possible. These regression models are implemented inside the NSGA-II algorithm for optimization. The optimal solution results show that using the applied multi-objective optimization method, it is possible to decrease the building's annual gas and electricity consumption, compared to the baseline case, by up to 21.3% and 9.7%, respectively, while keeping up the indoor environment in the limit of the thermal comfort zone.
学科与关键词
- Multi-objective optimization of building energy consumption and thermal comfort based on SVR-NSGA-IIWang, Ailing; Xiao, Ying; Liu, Chunlu; Zhao, Ying; Sun, Shaonan*Case Studies in Thermal Engineering, 2024, 63: 105368.被引 3
- Multiobjective optimization of building energy consumption and thermal comfort based on integrated BIM framework with machine learning-NSGA IIHosamo, Haidar Hosamo*; Tingstveit, Merethe Solvang; Nielsen, Henrik Kofoed; Svennevig, Paul Ragnar; Svidt, KjeldENERGY AND BUILDINGS, 2022, 277: 112479.被引 68
- Multi-objective optimization of residential building energy consumption, daylighting, and thermal comfort based on BO-XGBoost-NSGA-IIWu, Chengjin; Pan, Haize*; Luo, Zhenhua; Liu, Chuan; Huang, HulongyiBUILDING AND ENVIRONMENT, 2024, 254: 111386.被引 21
