Comparison of different meta model approches with a detailed buiding model for long-Term simulations

Johannes Maderspacher; Philipp Florian Geyer; Thomas Auer; Werner Lang

Details

Original language	English
Pages	106-113
Number of pages	8
Publication status	Published - 2015
Externally published	Yes
Event	14th Conference of International Building Performance Simulation Association, BS 2015 - Hyderabad, India Duration: 7 Dec 2015 → 9 Dec 2015

Conference

Conference	14th Conference of International Building Performance Simulation Association, BS 2015
Country/Territory	India
City	Hyderabad
Period	7 Dec 2015 → 9 Dec 2015

Abstract

If detailed building models are applied for long- Term simulations, for instance the prediction of the future energy demand under climate change, the computational effort can turn into a serious issue. Machine learning algorithms like Neural Networks (NN) or Support Vector Machine (SVM) could be an alternative. In this work a possible application of NN and SVM for long- Term forecasts are proven and their limitations are presented. In the examined case study, with a simulation period over 30 years, the SVM is hundred fifty times and the NN ten times faster than a detailed building model. This reduction of computational effort can be useful for further studies as a uncertainty analysis of climate change.

ASJC Scopus subject areas

Computer Science(all)
Computer Science Applications
Engineering(all)
Architecture
Mathematics(all)
Modelling and Simulation
Engineering(all)
Building and Construction

Sustainable Development Goals

SDG 13 - Climate Action

Cite this

Comparison of different meta model approches with a detailed buiding model for long-Term simulations. / Maderspacher, Johannes; Geyer, Philipp Florian; Auer, Thomas et al.
2015. 106-113 Paper presented at 14th Conference of International Building Performance Simulation Association, BS 2015, Hyderabad, India.

Research output: Contribution to conference › Paper › Research › peer review

Maderspacher, J, Geyer, PF, Auer, T & Lang, W 2015, 'Comparison of different meta model approches with a detailed buiding model for long-Term simulations', Paper presented at 14th Conference of International Building Performance Simulation Association, BS 2015, Hyderabad, India, 7 Dec 2015 - 9 Dec 2015 pp. 106-113.

Maderspacher, J., Geyer, P. F., Auer, T., & Lang, W. (2015). Comparison of different meta model approches with a detailed buiding model for long-Term simulations. 106-113. Paper presented at 14th Conference of International Building Performance Simulation Association, BS 2015, Hyderabad, India.

Maderspacher J, Geyer PF, Auer T, Lang W. Comparison of different meta model approches with a detailed buiding model for long-Term simulations. 2015. Paper presented at 14th Conference of International Building Performance Simulation Association, BS 2015, Hyderabad, India.

Maderspacher, Johannes ; Geyer, Philipp Florian ; Auer, Thomas et al. / Comparison of different meta model approches with a detailed buiding model for long-Term simulations. Paper presented at 14th Conference of International Building Performance Simulation Association, BS 2015, Hyderabad, India.8 p.

Download

@conference{10108b86eca5477e816e383e90410718,

title = "Comparison of different meta model approches with a detailed buiding model for long-Term simulations",

abstract = "If detailed building models are applied for long- Term simulations, for instance the prediction of the future energy demand under climate change, the computational effort can turn into a serious issue. Machine learning algorithms like Neural Networks (NN) or Support Vector Machine (SVM) could be an alternative. In this work a possible application of NN and SVM for long- Term forecasts are proven and their limitations are presented. In the examined case study, with a simulation period over 30 years, the SVM is hundred fifty times and the NN ten times faster than a detailed building model. This reduction of computational effort can be useful for further studies as a uncertainty analysis of climate change.",

author = "Johannes Maderspacher and Geyer, {Philipp Florian} and Thomas Auer and Werner Lang",

year = "2015",

language = "English",

pages = "106--113",

note = "14th Conference of International Building Performance Simulation Association, BS 2015 ; Conference date: 07-12-2015 Through 09-12-2015",

}

Download

TY - CONF

T1 - Comparison of different meta model approches with a detailed buiding model for long-Term simulations

AU - Maderspacher, Johannes

AU - Geyer, Philipp Florian

AU - Auer, Thomas

AU - Lang, Werner

PY - 2015

Y1 - 2015

N2 - If detailed building models are applied for long- Term simulations, for instance the prediction of the future energy demand under climate change, the computational effort can turn into a serious issue. Machine learning algorithms like Neural Networks (NN) or Support Vector Machine (SVM) could be an alternative. In this work a possible application of NN and SVM for long- Term forecasts are proven and their limitations are presented. In the examined case study, with a simulation period over 30 years, the SVM is hundred fifty times and the NN ten times faster than a detailed building model. This reduction of computational effort can be useful for further studies as a uncertainty analysis of climate change.

AB - If detailed building models are applied for long- Term simulations, for instance the prediction of the future energy demand under climate change, the computational effort can turn into a serious issue. Machine learning algorithms like Neural Networks (NN) or Support Vector Machine (SVM) could be an alternative. In this work a possible application of NN and SVM for long- Term forecasts are proven and their limitations are presented. In the examined case study, with a simulation period over 30 years, the SVM is hundred fifty times and the NN ten times faster than a detailed building model. This reduction of computational effort can be useful for further studies as a uncertainty analysis of climate change.

UR - http://www.scopus.com/inward/record.url?scp=84976407036&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84976407036

SP - 106

EP - 113

T2 - 14th Conference of International Building Performance Simulation Association, BS 2015

Y2 - 7 December 2015 through 9 December 2015

ER -

Research@Leibniz University