Development of a new energy benchmark for improving the operational rating system of office buildings using various data-mining techniques

As improving energy efficiency in buildings has become a global issue today, many countries have adopted the operational rating system to evaluate the energy performance of a building based on the actual energy consumption. A rational and reasonable energy benchmark can be used in the operational rating system to evaluate the energy performance of a building accurately and effectively. This study aims to develop a new energy benchmark for improving the operational rating system of office buildings. Toward this end, this study used various data-mining techniques such as correlation analysis, decision tree (DT) analysis, and analysis of variance (ANOVA). Based on data from 1072 office buildings in South Korea, this study was conducted in three steps: (i) Step 1: establishment of the database; (ii) Step 2: development of the new energy benchmark; and (iii) Step 3: application of the new energy benchmark for improving the operational rating system. As a result, six types of energy benchmarks for office buildings were developed using DT analysis based on the gross floor area (GFA) and the building use ratio (BUR) of offices, and these new energy benchmarks were validated using ANOVA. To ensure the effectiveness of the new energy benchmark, it was applied to three operational rating systems for comparison: (i) the baseline system (the same energy benchmark is used for all office buildings); (ii) the conventional system (different energy benchmarks are used depending on the GFA, currently used in South Korea); and (iii) the proposed system (different energy benchmarks are used depending on the GFA and the BUR of offices). The results of this study showed that the baseline and conventional operational rating system can be improved by using the new energy benchmark of the office building proposed in this study.

[1]  Fu Xiao,et al.  Quantitative energy performance assessment methods for existing buildings , 2012 .

[2]  Dejan Mumovic,et al.  Improved benchmarking comparability for energy consumption in schools , 2014 .

[3]  William Chung,et al.  Review of building energy-use performance benchmarking methodologies , 2011 .

[4]  Hyo Seon Park,et al.  Development of a new energy efficiency rating system for existing residential buildings , 2014 .

[5]  Zhengwei Li,et al.  Methods for benchmarking building energy consumption against its past or intended performance: An overview , 2014 .

[6]  Maria Kolokotroni,et al.  A method for energy classification of hotels: A case-study of Greece , 2012 .

[7]  Mischa Schmidt,et al.  Predictability of energy characteristics for cooling, ventilation and heating systems in sports facilities , 2015, 2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[8]  Taehoon Hong,et al.  A review on sustainable construction management strategies for monitoring, diagnosing, and retrofitting the building's dynamic energy performance: Focused on the operation and maintenance phase , 2015 .

[9]  Luis Pérez-Lombard,et al.  A review of benchmarking, rating and labelling concepts within the framework of building energy certification schemes , 2009 .

[10]  Ki-Hyung Yu,et al.  Analysis on Characteristics of the Energy Performance Index Depending on the Building Uses for Non-residential Building , 2014 .

[11]  Melek Yalcintas,et al.  An energy benchmarking model based on artificial neural network method utilizing US Commercial Buildings Energy Consumption Survey (CBECS) database , 2007 .

[12]  Mischa Schmidt,et al.  The energy efficiency problematics in sports facilities: identifying savings in daily grass heating operation , 2015, ICCPS.

[13]  Koen Steemers,et al.  Using Display Energy Certificates to quantify public sector office energy consumption , 2015 .

[14]  Endong Wang,et al.  Benchmarking whole-building energy performance with multi-criteria technique for order preference by similarity to ideal solution using a selective objective-weighting approach , 2015 .

[15]  Han Dong Wang.  Experimental Research on Performance of Heat Pump Using Shower Waste Water as Heat Source , 2011 .

[16]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[17]  Mohammad Yusri Hassan,et al.  Energy efficiency index as an indicator for measuring building energy performance: A review , 2015 .

[18]  Xuefeng Gao.  A new methodology for building energy benchmarking: An approach based on clustering concept and statistical models , 2013 .

[19]  David B. Goldstein,et al.  A classification of building energy performance indices , 2014 .

[20]  William Chung,et al.  A study of energy efficiency of private office buildings in Hong Kong , 2009 .

[21]  Lee Siew Eang,et al.  Benchmarking energy use and greenhouse gas emissions in Singapore's hotel industry , 2010 .

[22]  William Chung,et al.  Benchmarking the energy efficiency of commercial buildings , 2006 .

[23]  Taehoon Hong,et al.  Framework for establishing the optimal implementation strategy of a fuel-cell-based combined heat and power system: Focused on multi-family housing complex , 2014 .

[24]  Taehoon Hong,et al.  Development of a dynamic operational rating system in energy performance certificates for existing buildings: Geostatistical approach and data-mining technique , 2015 .

[25]  Melek Yalcintas,et al.  An energy benchmarking model based on artificial neural network method with a case example for tropical climates , 2006 .

[26]  Dejan Mumovic,et al.  Original Article/ResearchA comparative study of benchmarking approaches for non-domestic buildings: Part 1 – Top-down approach , 2013 .