Gradient boosting machine for modeling the energy consumption of commercial buildings
Abstract
Accurate savings estimations are important to promote energy efficiency projects and demonstrate their cost-effectiveness. The increasing presence of advanced metering infrastructure (AMI) in commercial buildings has resulted in a rising availability of high frequency interval data. These data can be used for a variety of energy efficiency applications such as demand response, fault detection and diagnosis, and heating, ventilation, and air conditioning (HVAC) optimization. This large amount of data has also opened the door to the use of advanced statistical learning models, which hold promise for providing accurate building baseline energy consumption predictions, and thus accurate saving estimations. The gradient boosting machine is a powerful machine learning algorithm that is gaining considerable traction in a wide range of data driven applications, such as ecology, computer vision, and biology. In the present work an energy consumption baseline modeling method based on a gradient boosting machine was proposed. To assess the performance of this method, a recently published testing procedure was used on a large dataset of 410 commercial buildings. The model training periods were varied and several prediction accuracy metrics were used to evaluate the model's performance. The results show that using the gradient boosting machine model improved the R-squared predictionmore »
- Authors:
-
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
- OSTI Identifier:
- 1439233
- Alternate Identifier(s):
- OSTI ID: 1496335
- Grant/Contract Number:
- AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Energy and Buildings
- Additional Journal Information:
- Journal Volume: 158; Journal Issue: C; Related Information: © 2017 Elsevier B.V.; Journal ID: ISSN 0378-7788
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Citation Formats
Touzani, Samir, Granderson, Jessica, and Fernandes, Samuel. Gradient boosting machine for modeling the energy consumption of commercial buildings. United States: N. p., 2017.
Web. doi:10.1016/j.enbuild.2017.11.039.
Touzani, Samir, Granderson, Jessica, & Fernandes, Samuel. Gradient boosting machine for modeling the energy consumption of commercial buildings. United States. https://doi.org/10.1016/j.enbuild.2017.11.039
Touzani, Samir, Granderson, Jessica, and Fernandes, Samuel. Sun .
"Gradient boosting machine for modeling the energy consumption of commercial buildings". United States. https://doi.org/10.1016/j.enbuild.2017.11.039. https://www.osti.gov/servlets/purl/1439233.
@article{osti_1439233,
title = {Gradient boosting machine for modeling the energy consumption of commercial buildings},
author = {Touzani, Samir and Granderson, Jessica and Fernandes, Samuel},
abstractNote = {Accurate savings estimations are important to promote energy efficiency projects and demonstrate their cost-effectiveness. The increasing presence of advanced metering infrastructure (AMI) in commercial buildings has resulted in a rising availability of high frequency interval data. These data can be used for a variety of energy efficiency applications such as demand response, fault detection and diagnosis, and heating, ventilation, and air conditioning (HVAC) optimization. This large amount of data has also opened the door to the use of advanced statistical learning models, which hold promise for providing accurate building baseline energy consumption predictions, and thus accurate saving estimations. The gradient boosting machine is a powerful machine learning algorithm that is gaining considerable traction in a wide range of data driven applications, such as ecology, computer vision, and biology. In the present work an energy consumption baseline modeling method based on a gradient boosting machine was proposed. To assess the performance of this method, a recently published testing procedure was used on a large dataset of 410 commercial buildings. The model training periods were varied and several prediction accuracy metrics were used to evaluate the model's performance. The results show that using the gradient boosting machine model improved the R-squared prediction accuracy and the CV(RMSE) in more than 80 percent of the cases, when compared to an industry best practice model that is based on piecewise linear regression, and to a random forest algorithm.},
doi = {10.1016/j.enbuild.2017.11.039},
journal = {Energy and Buildings},
number = C,
volume = 158,
place = {United States},
year = {Sun Nov 26 00:00:00 EST 2017},
month = {Sun Nov 26 00:00:00 EST 2017}
}
Web of Science
Works referenced in this record:
Search for direct top-squark pair production in final states with two leptons in pp collisions at $ \sqrt{s} $ = 8 TeV with the ATLAS detector
journal, June 2014
- Aad, G.; Abajyan, T.; Abbott, B.
- Journal of High Energy Physics, Vol. 2014, Issue 6
Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption
journal, July 2017
- Ahmad, Muhammad Waseem; Mourshed, Monjur; Rezgui, Yacine
- Energy and Buildings, Vol. 147
An ensemble learning framework for anomaly detection in building energy consumption
journal, June 2017
- Araya, Daniel B.; Grolinger, Katarina; ElYamany, Hany F.
- Energy and Buildings, Vol. 144
On the use of cross-validation for time series predictor evaluation
journal, May 2012
- Bergmeir, Christoph; Benítez, José M.
- Information Sciences, Vol. 191
Kernel regression for real-time building energy analysis
journal, July 2012
- Brown, Matthew; Barrington-Leigh, Chris; Brown †, Zosia
- Journal of Building Performance Simulation, Vol. 5, Issue 4
Measurement and verification of building systems under uncertain data: A Gaussian process modeling approach
journal, June 2014
- Burkhart, Michael C.; Heo, Yeonsook; Zavala, Victor M.
- Energy and Buildings, Vol. 75
Stochastic gradient boosting
journal, February 2002
- Friedman, Jerome H.
- Computational Statistics & Data Analysis, Vol. 38, Issue 4
Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors)
journal, April 2000
- Friedman, Jerome; Hastie, Trevor; Tibshirani, Robert
- The Annals of Statistics, Vol. 28, Issue 2
Boosting a Weak Learning Algorithm by Majority
journal, September 1995
- Freund, Y.
- Information and Computation, Vol. 121, Issue 2
Extremely randomized trees
journal, March 2006
- Geurts, Pierre; Ernst, Damien; Wehenkel, Louis
- Machine Learning, Vol. 63, Issue 1
Automated measurement and verification: Performance of public domain whole-building electric baseline models
journal, April 2015
- Granderson, Jessica; Price, Phillip N.; Jump, David
- Applied Energy, Vol. 144
Accuracy of automated measurement and verification (M&V) techniques for energy savings in commercial buildings
journal, July 2016
- Granderson, Jessica; Touzani, Samir; Custodio, Claudine
- Applied Energy, Vol. 173
Application of automated measurement and verification to utility energy efficiency program data
journal, May 2017
- Granderson, Jessica; Touzani, Samir; Fernandes, Samuel
- Energy and Buildings, Vol. 142
Gaussian process modeling for measurement and verification of building energy savings
journal, October 2012
- Heo, Yeonsook; Zavala, Victor M.
- Energy and Buildings, Vol. 53
Quantifying Changes in Building Electricity Use, With Application to Demand Response
journal, September 2011
- Mathieu, Johanna L.; Price, Phillip N.; Kiliccote, Sila
- IEEE Transactions on Smart Grid, Vol. 2, Issue 3
A comparison of random forests, boosting and support vector machines for genomic selection
journal, May 2011
- Ogutu, Joseph O.; Piepho, Hans-Peter; Schulz-Streeck, Torben
- BMC Proceedings, Vol. 5, Issue S3
Comparison of five modelling techniques to predict the spatial distribution and abundance of seabirds
journal, November 2012
- Oppel, Steffen; Meirinho, Ana; Ramírez, Iván
- Biological Conservation, Vol. 156
Understanding how roadside concentrations of NO x are influenced by the background levels, traffic density, and meteorological conditions using Boosted Regression Trees
journal, February 2016
- Sayegh, Arwa; Tate, James E.; Ropkins, Karl
- Atmospheric Environment, Vol. 127
The strength of weak learnability
journal, June 1990
- Schapire, Robert E.
- Machine Learning, Vol. 5, Issue 2
Baseline building energy modeling and localized uncertainty quantification using Gaussian mixture models
journal, October 2013
- Srivastav, Abhishek; Tewari, Ashutosh; Dong, Bing
- Energy and Buildings, Vol. 65
A review on the prediction of building energy consumption
journal, August 2012
- Zhao, Hai-xiang; Magoulès, Frédéric
- Renewable and Sustainable Energy Reviews, Vol. 16, Issue 6
Works referencing / citing this record:
Management and monitoring of the displaced commercial risk: a prescriptive approach
journal, January 2020
- Touri, Othmane; Ahroum, Rida; Achchab, Boujemâa
- International Journal of Emerging Markets, Vol. ahead-of-print, Issue ahead-of-print
Coupled Least Squares Support Vector Ensemble Machines
journal, June 2019
- Wornyo, Dickson Keddy; Shen, Xiang-Jun
- Information, Vol. 10, Issue 6
How do data-mining models consider arsenic contamination in sediments and variables importance?
journal, November 2019
- Mirchooli, Fahimeh; Motevalli, Alireza; Pourghasemi, Hamid Reza
- Environmental Monitoring and Assessment, Vol. 191, Issue 12
Prediction of higher heating value of biomass materials based on proximate analysis using gradient boosted regression trees method
journal, July 2019
- Samadi, Seyed Hashem; Ghobadian, Barat; Nosrati, Mohsen
- Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
Load Forecasting for a Campus University Using Ensemble Methods Based on Regression Trees
journal, August 2018
- Ruiz-Abellón, María; Gabaldón, Antonio; Guillamón, Antonio
- Energies, Vol. 11, Issue 8
Data Driven Natural Gas Spot Price Prediction Models Using Machine Learning Methods
journal, May 2019
- Su, Moting; Zhang, Zongyi; Zhu, Ye
- Energies, Vol. 12, Issue 9
Forecasting Energy Use in Buildings Using Artificial Neural Networks: A Review
journal, August 2019
- Runge, Jason; Zmeureanu, Radu
- Energies, Vol. 12, Issue 17
Uncertainy’s Indices Assessment for Calibrated Energy Models
journal, May 2019
- González, Vicente Gutiérrez; Colmenares, Lissette Álvarez; Fidalgo, Jesús Fernando López
- Energies, Vol. 12, Issue 11
Inference from Non-Probability Surveys with Statistical Matching and Propensity Score Adjustment Using Modern Prediction Techniques
journal, June 2020
- Castro-Martín, Luis; Rueda, Maria del Mar; Ferri-García, Ramón
- Mathematics, Vol. 8, Issue 6
Simulation and Optimisation of Air Conditioning Systems using Machine Learning
text, January 2020
- Godahewa, Rakshitha; Deng, Chang; Prouzeau, Arnaud
- arXiv
Predicting Higher Education Throughput in South Africa Using a Tree-Based Ensemble Technique
preprint, January 2021
- Mbuvha, Rendani; Zondo, Patience; Mauda, Aluwani
- arXiv