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 -