Application of data mining techniques for building simulation performance prediction analysis

Christoph Morbitzer, Paul Strachan, Catherine Simpson

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Simulation exercises covering long periods (e.g.. annual simulations) can produce large quantities of data. The result data set is often primarily used to determine key performance parameters such as the frequency binning of internal temperatures. Efforts to obtain an understanding for reasons behind the predicted building performance are often only carried out to a limited extent and simulation is therefore not used to its full potential. This paper describes how data mining can be used to enhance the analysis of results obtained from a simulation exercise. It identifies clustering as a particular useful analysis technique and illustrates its potential in enhancing the analysis of building simulation performance predictions.
LanguageEnglish
Title of host publicationProceedings of the 8th International Building Performance Simulation Association Conference
Publication statusPublished - 2003

Fingerprint

Data mining
Temperature

Keywords

  • architecture
  • building simulation
  • building design
  • building performance
  • data mining

Cite this

Morbitzer, C., Strachan, P., & Simpson, C. (2003). Application of data mining techniques for building simulation performance prediction analysis. In Proceedings of the 8th International Building Performance Simulation Association Conference
Morbitzer, Christoph ; Strachan, Paul ; Simpson, Catherine. / Application of data mining techniques for building simulation performance prediction analysis. Proceedings of the 8th International Building Performance Simulation Association Conference. 2003.
@inbook{365c3766e46e4004b824220bbf99e2ae,
title = "Application of data mining techniques for building simulation performance prediction analysis",
abstract = "Simulation exercises covering long periods (e.g.. annual simulations) can produce large quantities of data. The result data set is often primarily used to determine key performance parameters such as the frequency binning of internal temperatures. Efforts to obtain an understanding for reasons behind the predicted building performance are often only carried out to a limited extent and simulation is therefore not used to its full potential. This paper describes how data mining can be used to enhance the analysis of results obtained from a simulation exercise. It identifies clustering as a particular useful analysis technique and illustrates its potential in enhancing the analysis of building simulation performance predictions.",
keywords = "architecture, building simulation, building design, building performance, data mining",
author = "Christoph Morbitzer and Paul Strachan and Catherine Simpson",
year = "2003",
language = "English",
booktitle = "Proceedings of the 8th International Building Performance Simulation Association Conference",

}

Morbitzer, C, Strachan, P & Simpson, C 2003, Application of data mining techniques for building simulation performance prediction analysis. in Proceedings of the 8th International Building Performance Simulation Association Conference.

Application of data mining techniques for building simulation performance prediction analysis. / Morbitzer, Christoph; Strachan, Paul; Simpson, Catherine.

Proceedings of the 8th International Building Performance Simulation Association Conference. 2003.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

TY - CHAP

T1 - Application of data mining techniques for building simulation performance prediction analysis

AU - Morbitzer, Christoph

AU - Strachan, Paul

AU - Simpson, Catherine

PY - 2003

Y1 - 2003

N2 - Simulation exercises covering long periods (e.g.. annual simulations) can produce large quantities of data. The result data set is often primarily used to determine key performance parameters such as the frequency binning of internal temperatures. Efforts to obtain an understanding for reasons behind the predicted building performance are often only carried out to a limited extent and simulation is therefore not used to its full potential. This paper describes how data mining can be used to enhance the analysis of results obtained from a simulation exercise. It identifies clustering as a particular useful analysis technique and illustrates its potential in enhancing the analysis of building simulation performance predictions.

AB - Simulation exercises covering long periods (e.g.. annual simulations) can produce large quantities of data. The result data set is often primarily used to determine key performance parameters such as the frequency binning of internal temperatures. Efforts to obtain an understanding for reasons behind the predicted building performance are often only carried out to a limited extent and simulation is therefore not used to its full potential. This paper describes how data mining can be used to enhance the analysis of results obtained from a simulation exercise. It identifies clustering as a particular useful analysis technique and illustrates its potential in enhancing the analysis of building simulation performance predictions.

KW - architecture

KW - building simulation

KW - building design

KW - building performance

KW - data mining

UR - http://www.ibpsa.org/proceedings/BS2003/BS03_0911_918.pdf

M3 - Chapter

BT - Proceedings of the 8th International Building Performance Simulation Association Conference

ER -

Morbitzer C, Strachan P, Simpson C. Application of data mining techniques for building simulation performance prediction analysis. In Proceedings of the 8th International Building Performance Simulation Association Conference. 2003

Access to Document