Machine learning approaches for estimating commercial building energy consumption

Caleb Robinson, Bistra Dilkina, Jeffrey Hubbs, Wenwen Zhang, Subhrajit Guhathakurta, Marilyn A. Brown, Ram Pendyala

Research output: Contribution to journalArticle

49 Citations (Scopus)

Abstract

Building energy consumption makes up 40% of the total energy consumption in the United States. Given that energy consumption in buildings is influenced by aspects of urban form such as density and floor-area-ratios (FAR), understanding the distribution of energy intensities is critical for city planners. This paper presents a novel technique for estimating commercial building energy consumption from a small number of building features by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Our results show that gradient boosting regression models perform the best at predicting commercial building energy consumption, and can make predictions that are on average within a factor of 2 from the true energy consumption values (with an r2 score of 0.82). We validate our models using the New York City Local Law 84 energy consumption dataset, then apply them to the city of Atlanta to create aggregate energy consumption estimates. In general, the models developed only depend on five commonly accessible building and climate features, and can therefore be applied to diverse metropolitan areas in the United States and to other countries through replication of our methodology.

Original languageEnglish (US)
JournalApplied Energy
DOIs
StateAccepted/In press - 2017

Fingerprint

Learning systems
Energy utilization
energy consumption
machine learning
metropolitan area
methodology
climate
prediction
energy
city

Keywords

  • 00-01
  • 99-00
  • CBECS
  • Commercial building energy consumption
  • Machine learning
  • Modeling

ASJC Scopus subject areas

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

Cite this

Robinson, C., Dilkina, B., Hubbs, J., Zhang, W., Guhathakurta, S., Brown, M. A., & Pendyala, R. (Accepted/In press). Machine learning approaches for estimating commercial building energy consumption. Applied Energy. https://doi.org/10.1016/j.apenergy.2017.09.060

Machine learning approaches for estimating commercial building energy consumption. / Robinson, Caleb; Dilkina, Bistra; Hubbs, Jeffrey; Zhang, Wenwen; Guhathakurta, Subhrajit; Brown, Marilyn A.; Pendyala, Ram.

In: Applied Energy, 2017.

Research output: Contribution to journalArticle

Robinson, Caleb ; Dilkina, Bistra ; Hubbs, Jeffrey ; Zhang, Wenwen ; Guhathakurta, Subhrajit ; Brown, Marilyn A. ; Pendyala, Ram. / Machine learning approaches for estimating commercial building energy consumption. In: Applied Energy. 2017.
@article{2b464a8f28ee4580bf9313944daac5e6,
title = "Machine learning approaches for estimating commercial building energy consumption",
abstract = "Building energy consumption makes up 40{\%} of the total energy consumption in the United States. Given that energy consumption in buildings is influenced by aspects of urban form such as density and floor-area-ratios (FAR), understanding the distribution of energy intensities is critical for city planners. This paper presents a novel technique for estimating commercial building energy consumption from a small number of building features by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Our results show that gradient boosting regression models perform the best at predicting commercial building energy consumption, and can make predictions that are on average within a factor of 2 from the true energy consumption values (with an r2 score of 0.82). We validate our models using the New York City Local Law 84 energy consumption dataset, then apply them to the city of Atlanta to create aggregate energy consumption estimates. In general, the models developed only depend on five commonly accessible building and climate features, and can therefore be applied to diverse metropolitan areas in the United States and to other countries through replication of our methodology.",
keywords = "00-01, 99-00, CBECS, Commercial building energy consumption, Machine learning, Modeling",
author = "Caleb Robinson and Bistra Dilkina and Jeffrey Hubbs and Wenwen Zhang and Subhrajit Guhathakurta and Brown, {Marilyn A.} and Ram Pendyala",
year = "2017",
doi = "10.1016/j.apenergy.2017.09.060",
language = "English (US)",
journal = "Applied Energy",
issn = "0306-2619",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Machine learning approaches for estimating commercial building energy consumption

AU - Robinson, Caleb

AU - Dilkina, Bistra

AU - Hubbs, Jeffrey

AU - Zhang, Wenwen

AU - Guhathakurta, Subhrajit

AU - Brown, Marilyn A.

AU - Pendyala, Ram

PY - 2017

Y1 - 2017

N2 - Building energy consumption makes up 40% of the total energy consumption in the United States. Given that energy consumption in buildings is influenced by aspects of urban form such as density and floor-area-ratios (FAR), understanding the distribution of energy intensities is critical for city planners. This paper presents a novel technique for estimating commercial building energy consumption from a small number of building features by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Our results show that gradient boosting regression models perform the best at predicting commercial building energy consumption, and can make predictions that are on average within a factor of 2 from the true energy consumption values (with an r2 score of 0.82). We validate our models using the New York City Local Law 84 energy consumption dataset, then apply them to the city of Atlanta to create aggregate energy consumption estimates. In general, the models developed only depend on five commonly accessible building and climate features, and can therefore be applied to diverse metropolitan areas in the United States and to other countries through replication of our methodology.

AB - Building energy consumption makes up 40% of the total energy consumption in the United States. Given that energy consumption in buildings is influenced by aspects of urban form such as density and floor-area-ratios (FAR), understanding the distribution of energy intensities is critical for city planners. This paper presents a novel technique for estimating commercial building energy consumption from a small number of building features by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Our results show that gradient boosting regression models perform the best at predicting commercial building energy consumption, and can make predictions that are on average within a factor of 2 from the true energy consumption values (with an r2 score of 0.82). We validate our models using the New York City Local Law 84 energy consumption dataset, then apply them to the city of Atlanta to create aggregate energy consumption estimates. In general, the models developed only depend on five commonly accessible building and climate features, and can therefore be applied to diverse metropolitan areas in the United States and to other countries through replication of our methodology.

KW - 00-01

KW - 99-00

KW - CBECS

KW - Commercial building energy consumption

KW - Machine learning

KW - Modeling

UR - http://www.scopus.com/inward/record.url?scp=85030639721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030639721&partnerID=8YFLogxK

U2 - 10.1016/j.apenergy.2017.09.060

DO - 10.1016/j.apenergy.2017.09.060

M3 - Article

AN - SCOPUS:85030639721

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

ER -