Benchmarking Evaluation of Building Energy Consumption Based on Data Mining

Thomas Wu, Bo Wang, Dongdong Zhang (), Ziwei Zhao and Hongyu Zhu ()
Additional contact information
Thomas Wu: School of Electrical Engineering, Guangxi University, Nanning 530004, China
Bo Wang: School of Electrical Engineering, Guangxi University, Nanning 530004, China
Dongdong Zhang: School of Electrical Engineering, Guangxi University, Nanning 530004, China
Ziwei Zhao: School of Electrical Engineering, Guangxi University, Nanning 530004, China
Hongyu Zhu: School of Electrical Engineering, Guangxi University, Nanning 530004, China

Sustainability, 2023, vol. 15, issue 6, 1-16

Abstract: University building energy consumption is an important proportion of the total energy consumption of society. In order to work out the problem of poor practicability of the existing benchmarking management method of campus building energy consumption, this study proposes an evaluation model of campus building energy consumption benchmarking management. By analyzing several types of feature data of buildings, this study uses random forest method to determine the building features that have outstanding contributions to building energy consumption intensity and building classification, and uses the K-means method to reclassify buildings based on the building features obtained after screening, to obtain a building category that is more in line with the actual use situation and to solve the problem that the existing building classification is not in line with the reality. Compared with the original classification method, the new classification method showed significant improvement in many indexes, among which DBI decreased by 60.8% and CH increased by 3.73 times. Finally, the quart lines of buildings in the category of new buildings are calculated to obtain the low energy consumption line, medium energy consumption line and high energy consumption line of buildings, so as to improve the accuracy and practicability of energy consumption line classification.

Keywords: building energy consumption; benchmarking; data mining; random forest model; factor analysis; K-means cluster (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/6/5211/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/6/5211/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:6:p:5211-:d:1098004

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().