TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. Automated classification and identification procedure for prediction of energy consumption in multi-mode buildings
 
Options

Automated classification and identification procedure for prediction of energy consumption in multi-mode buildings

Publikationstyp
Conference Paper
Date Issued
2017-09
Sprache
English
Author(s)
Khosravi, Mohammad  
Eichler, Annika  
Smith, Roy S.  
TORE-URI
http://hdl.handle.net/11420/12785
First published in
Energy procedia  
Number in series
122
Start Page
1021
End Page
1026
Citation
Energy Procedia 122: 1021-1026 (2017)
Contribution to Conference
14th International Scientific Conference - Future Buildings & Districts - Energy Efficiency from Nano to Urban Scale, CISBAT 2017  
Publisher DOI
10.1016/j.egypro.2017.07.469
Scopus ID
2-s2.0-85029902410
Publisher
Elsevier
With an increasing share of renewable energy sources, largely decentralized, energy hubs are gaining relevance in the energy landscape as promising solutions because they match local production with consumption. To efficiently control an energy hub a prediction of the energy consumption of the buildings in the hub is required. This work proposes an on-line identification scheme to identify the closed-loop behavior of buildings as they are usually under unknown local lower-level control. Since buildings are typically controlled in different modes depending on the time of day (night setback), an identification of a switched system is proposed, combining a classification step to identify the switching times followed by the identification of a piecewise linear model for each mode. As a test case an operational Swiss office building is considered.
Subjects
classification
Energy Hubs
energy management
identification
piece-wise linear regression
switched systems
DDC Class
004: Informatik
More Funding Information
This work was supported by CTI over the project SCCER FEEB&D.
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback