A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Parameter estimation for building energy models using GRcGAN
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.
Parameter estimation for building energy models using GRcGAN
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.
Parameter estimation for building energy models using GRcGAN
Build. Simul.
Shin, Hansol (author) / Park, Cheol-Soo (author)
Building Simulation ; 16 ; 629-639
2023-04-01
11 pages
Article (Journal)
Electronic Resource
English
generative adversarial networks , generative model , parameter estimation , inverse problem , model calibration , parameter uncertainty Engineering , Building Construction and Design , Engineering Thermodynamics, Heat and Mass Transfer , Atmospheric Protection/Air Quality Control/Air Pollution , Monitoring/Environmental Analysis
| British Library Online Contents | 2018
| British Library Online Contents | 2018
| British Library Online Contents | 2018
Parameter Estimation for Muskingum Models
| British Library Online Contents | 2004
A novel efficient optimization algorithm for parameter estimation of building thermal dynamic models
| British Library Online Contents | 2019