KIT | KIT-Bibliothek | Impressum | Datenschutz

Clustering the Occupant Behavior in Residential Buildings : a Method Comparison

Carbonare, Nicolás ORCID iD icon; Pflug, T.; Wagner, Andreas ORCID iD icon

Abstract:

The aim of this paper is to investigate possible patterns of the occupant behaviour in residential buildings. Measurements were taken in multifamily buildings where several occupantrelated variables were recorded. We chose and compared two different clustering methods: whole time series and features clustering (kmeans algorithm). The mentioned methods were performed selecting two variables (window opening and indoor temperature), and tested with supervised learning methods. Results suggest that features clustering can perform better than whole time series. The representation of the occupant behaviour through features is meant to be applied in future work regarding the optimization of control strategies in ventilation systems.


Verlagsausgabe §
DOI: 10.5445/IR/1000085746
Veröffentlicht am 23.10.2018
Cover der Publikation
Zugehörige Institution(en) am KIT Fakultät für Architektur – Fachgebiet Bauphysik und Technischer Ausbau (fbta)
Institut Entwerfen und Bautechnik (IEB)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2018
Sprache Englisch
Identifikator urn:nbn:de:swb:90-857460
KITopen-ID: 1000085746
Erschienen in BauSIM2018 - 7. Deutsch-Österreichische IBPSA-Konferenz : Tagungsband. Hrsg.: P. von Both
Verlag Karlsruher Institut für Technologie (KIT)
Seiten 187-194
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page