An estimation methodology for the dynamic operational rating of a new residential building using the advanced case-based reasoning and stochastic approaches

Taehoon Hong, Choongwan Koo, Daeho Kim, Minhyun Lee, Jimin Kim

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

To ensure the high energy performance of a new building, its operational rating should be accurately estimated in the early design phase. Toward this end, this study developed an estimation methodology for the dynamic operational rating (DOR) of a new residential building using the advanced case-based reasoning (A-CBR) and stochastic approaches. This study was conducted in three steps: (i) establishment of a case database; (ii) retrieval of similar cases using the A-CBR approach; and (iii) estimation of the dynamic operational rating using the stochastic approach. The residential buildings located in Pusan, South Korea, were selected to validate the applicability of the developed methodology. Also, this study used the mean absolute percentage error (MAPE) to evaluate the prediction accuracy of the developed methodology (which means the difference between the predicted and measured energy performance). As a result, it was determined that the MAPE of the A-CBR model (i.e., 96.8% for electricity and 86.6% for gas energy) is superior to those of the other models (i.e., the basic CBR, multiple regression analysis, and artificial neural network models). In addition, based on the stochastic approach, it was estimated that cluster No.6, as a case study, would have the letter rating of '. B' grade (i.e., 25. <. DOR. ≤. 50) with 83.46% of probability; and the letter rating of. C' grade (i.e., 50. <. DOR. ≤. 75) with 16.54%. The developed methodology can be used to easily and accurately estimate the dynamic operational rating of a new residential building in the early design phase.

Original languageEnglish
Pages (from-to)308-322
Number of pages15
JournalApplied Energy
Volume150
DOIs
Publication statusPublished - 2015 Jul 5

All Science Journal Classification (ASJC) codes

  • Building and Construction
  • Energy(all)
  • Mechanical Engineering
  • Management, Monitoring, Policy and Law

Fingerprint Dive into the research topics of 'An estimation methodology for the dynamic operational rating of a new residential building using the advanced case-based reasoning and stochastic approaches'. Together they form a unique fingerprint.

  • Cite this