Influence of error terms in Bayesian calibration of energy system models

Kathrin Menberg, Yeonsook Heo, Ruchi Choudhary

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Calibration represents a crucial step in the modelling process to obtain accurate simulation results and quantify uncertainties. We scrutinize the statistical Kennedy & O’Hagan framework, which quantifies different sources of uncertainty in the calibration process, including both model inputs and errors in the model. In specific, we evaluate the influence of error terms on the posterior predictions of calibrated model inputs. We do so by using a simulation model of a heat pump in cooling mode. While posterior values of many parameters concur with the expectations, some parameters appear not to be inferable. This is particularly true for parameters associated with model discrepancy, for which prior knowledge is typically scarce. We reveal the importance of assessing the identifiability of parameters by exploring the dependency of posteriors on the assigned prior knowledge. Analyses with random datasets show that results are overall consistent, which confirms the applicability and reliability of the framework.

Original languageEnglish
Pages (from-to)82-96
Number of pages15
JournalJournal of Building Performance Simulation
Volume12
Issue number1
DOIs
Publication statusPublished - 2019 Jan 2

Fingerprint

Error term
Calibration
Energy
Prior Knowledge
Quantify
Uncertainty
Identifiability
Process Modeling
Model
Pump
Discrepancy
Cooling
Simulation Model
Heat
Influence
Pumps
Evaluate
Prediction
Simulation
Framework

Keywords

  • Bayesian inference
  • building energy model
  • energy system model
  • inverse problems
  • model calibration
  • uncertainty quantification

ASJC Scopus subject areas

  • Architecture
  • Building and Construction
  • Modelling and Simulation
  • Computer Science Applications

Cite this

Influence of error terms in Bayesian calibration of energy system models. / Menberg, Kathrin; Heo, Yeonsook; Choudhary, Ruchi.

In: Journal of Building Performance Simulation, Vol. 12, No. 1, 02.01.2019, p. 82-96.

Research output: Contribution to journalArticle

@article{d1486c1703b145e39768af5ebf89cac4,
title = "Influence of error terms in Bayesian calibration of energy system models",
abstract = "Calibration represents a crucial step in the modelling process to obtain accurate simulation results and quantify uncertainties. We scrutinize the statistical Kennedy & O’Hagan framework, which quantifies different sources of uncertainty in the calibration process, including both model inputs and errors in the model. In specific, we evaluate the influence of error terms on the posterior predictions of calibrated model inputs. We do so by using a simulation model of a heat pump in cooling mode. While posterior values of many parameters concur with the expectations, some parameters appear not to be inferable. This is particularly true for parameters associated with model discrepancy, for which prior knowledge is typically scarce. We reveal the importance of assessing the identifiability of parameters by exploring the dependency of posteriors on the assigned prior knowledge. Analyses with random datasets show that results are overall consistent, which confirms the applicability and reliability of the framework.",
keywords = "Bayesian inference, building energy model, energy system model, inverse problems, model calibration, uncertainty quantification",
author = "Kathrin Menberg and Yeonsook Heo and Ruchi Choudhary",
year = "2019",
month = "1",
day = "2",
doi = "10.1080/19401493.2018.1475506",
language = "English",
volume = "12",
pages = "82--96",
journal = "Journal of Building Performance Simulation",
issn = "1940-1493",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Influence of error terms in Bayesian calibration of energy system models

AU - Menberg, Kathrin

AU - Heo, Yeonsook

AU - Choudhary, Ruchi

PY - 2019/1/2

Y1 - 2019/1/2

N2 - Calibration represents a crucial step in the modelling process to obtain accurate simulation results and quantify uncertainties. We scrutinize the statistical Kennedy & O’Hagan framework, which quantifies different sources of uncertainty in the calibration process, including both model inputs and errors in the model. In specific, we evaluate the influence of error terms on the posterior predictions of calibrated model inputs. We do so by using a simulation model of a heat pump in cooling mode. While posterior values of many parameters concur with the expectations, some parameters appear not to be inferable. This is particularly true for parameters associated with model discrepancy, for which prior knowledge is typically scarce. We reveal the importance of assessing the identifiability of parameters by exploring the dependency of posteriors on the assigned prior knowledge. Analyses with random datasets show that results are overall consistent, which confirms the applicability and reliability of the framework.

AB - Calibration represents a crucial step in the modelling process to obtain accurate simulation results and quantify uncertainties. We scrutinize the statistical Kennedy & O’Hagan framework, which quantifies different sources of uncertainty in the calibration process, including both model inputs and errors in the model. In specific, we evaluate the influence of error terms on the posterior predictions of calibrated model inputs. We do so by using a simulation model of a heat pump in cooling mode. While posterior values of many parameters concur with the expectations, some parameters appear not to be inferable. This is particularly true for parameters associated with model discrepancy, for which prior knowledge is typically scarce. We reveal the importance of assessing the identifiability of parameters by exploring the dependency of posteriors on the assigned prior knowledge. Analyses with random datasets show that results are overall consistent, which confirms the applicability and reliability of the framework.

KW - Bayesian inference

KW - building energy model

KW - energy system model

KW - inverse problems

KW - model calibration

KW - uncertainty quantification

UR - http://www.scopus.com/inward/record.url?scp=85047186012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047186012&partnerID=8YFLogxK

U2 - 10.1080/19401493.2018.1475506

DO - 10.1080/19401493.2018.1475506

M3 - Article

AN - SCOPUS:85047186012

VL - 12

SP - 82

EP - 96

JO - Journal of Building Performance Simulation

JF - Journal of Building Performance Simulation

SN - 1940-1493

IS - 1

ER -