Parameter estimation for building energy models using GRcGAN

被引：0
作者：
Hansol Shin
Cheol-Soo Park
机构：
[1] Seoul National University,Department of Architecture and Architectural Engineering, College of Engineering
[2] Seoul National University,Institute of Construction and Environmental Engineering, Institute of Engineering Research, College of Engineering
来源：
Building Simulation | 2023年 / 16卷
关键词：
generative adversarial networks; generative model; parameter estimation; inverse problem; model calibration; parameter uncertainty;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Parameter estimation methods can be classified into (1) manual (trial-and-error), (2) numerical optimization (optimization, sampling), (3) Bayesian inference (Bayes filter, Bayesian calibration), and (4) machine learning (generative model). Bayesian calibration has been widely used because it can capture stochastic nature of uncertain parameters. However, the results of Bayesian calibration could be biased by (1) the prior distribution assumed by the expert’s subjective judgment; (2) the likelihood function that cannot always describe the true likelihood; and (3) the posterior distribution approximation method, such as the Markov Chain Monte Carlo, which requires significant computation time. To overcome this, a new approach using a generator-regularized continuous conditional generative adversarial network (GRcGAN) is presented in this paper. Five target parameters of the DOE reference building model were selected. GRcGAN was trained to estimate uncertain parameters using simulated monthly electricity and gas use. GRcGAN can successfully estimate five uncertain parameters based on 1,000 training data points. The proposed approach presents a potential for stochastic parameter estimation.
引用
收藏
页码：629 / 639
页数：10
相关论文
共 130 条
  • [1] Bendaoud NMM(2021)Comparing Generative Adversarial Networks architectures for electricity demand forecasting Energy and Buildings 247 111152-210
  • [2] Farah N(2019)Parameter estimation for externally simulated thermal network models Energy and Buildings 191 200-483
  • [3] Ben Ahmed S(2019)Development and validation of an HVAC on/off controller in EnergyPlus for energy simulation of residential and small commercial buildings Energy and Buildings 183 467-379
  • [4] Brastein OM(2021)Scalable Bayesian optimization for model calibration: case study on coupled building and HVAC dynamics Energy and Buildings 253 111460-355
  • [5] Lie B(2018)Building occupancy modeling using generative adversarial network Energy and Buildings 174 372-547
  • [6] Sharma R(2020)Automatic and rapid calibration of urban building energy models by learning from energy performance database Applied Energy 277 115584-103
  • [7] Skeie NO(2017)Bayesian calibration of building energy models with large datasets Energy and Buildings 154 343-385
  • [8] Cetin KS(2018)Guidelines for the Bayesian calibration of building energy models Energy and Buildings 174 527-49
  • [9] Fathollahzadeh MH(2013)ROBESim: A retrofit-oriented building energy simulator based on EnergyPlus Energy and Buildings 66 88-958
  • [10] Kunwar N(2015)Evaluation of a multi-stage guided search approach for the calibration of building energy simulation models Energy and Buildings 87 370-91
12345678910