Journal
APPLIED ENERGY
Volume 91, Issue 1, Pages 146-155Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.apenergy.2011.09.023
Keywords
Data Mining; District heating; Supervision; FDD; KLT; Billing system
Categories
Ask authors/readers for more resources
An application of algorithmic exploration of billing data is examined for fault detection, diagnosis (FDD) based on evaluation of present state and detection of unexpected changes in energy efficiency of buildings. Large data sets from district heating (DH) billing systems are used for construction of feature space, diagnostic rules and classification of the buildings according to their energy efficiency properties. The algorithmic approach automates discovering knowledge about common, thus accepted changes in buildings' properties, in equipment and in habitants' behavior reflecting progress in technology and life style. In this article implementation of Data Mining and Knowledge Discovery (DMKD) method in supervision system with exemplary results based on real data is presented. Crucial steps of data processing influencing diagnostic results are described in details. (C) 2011 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available