research-article

Building Energy Consumption Forecasting: A Comparison of Gradient Boosting Models

Authors:

Hanna Sigurdson,

Connor Glossop,

Jonathan H. ChanAuthors Info & Claims

IAIT '21: Proceedings of the 12th International Conference on Advances in Information Technology

Article No.: 27, Pages 1 - 9

https://doi.org/10.1145/3468784.3470656

Published: 20 July 2021 Publication History

Abstract

Abstract: Building energy consumption forecasting is essential for improving the sustainability of buildings in the context of addressing climate change. Accurate building load predictions are useful for energy efficient building design selection and demand-side management initiatives. Using historical building energy consumption data has allowed researchers to develop machine learning models to improve the accuracy of such predictions, beyond inefficient traditional approaches otherwise used by the building sector. This work examines gradient boosting machine learning models, namely LightGBM, CatBoost, and XGBoost, for the purpose of comparing their performance on a select dataset. These gradient boosting models are popular in Kaggle machine learning contest solutions but have not been compared formally for the application of building energy consumption predictions. This work applies the three gradient boosting algorithms to a synthesized dataset for a large office building in Chicago. Preliminary results from the presented comparison demonstrate that XGBoost performs better than LightGBM and CatBoost when trained on the selected dataset.

References

[1]

Mabrook Al-Rakhami, Abdu Gumaei, Ahmed Alsanad, Atif Alamri, and Mohammad Mehedi Hassan. 2019. An Ensemble Learning Approach for Accurate Energy Load Prediction in Residential Buildings. IEEE Access 7(2019), 48328–48338. https://doi.org/10.1109/ACCESS.2019.2909470

[2]

Kadir Amasyali and Nora M. El-Gohary. 2018. A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews 81, 1 (Jan. 2018), 1192–1205. https://doi.org/10.1016/j.rser.2017.04.095

[3]

ASHRAE. 2019. ASHRAE - Great Energy Predictor III. https://www.kaggle.com/c/ashrae-energy-prediction

[4]

Candice Bentéjac, Anna Csörgő, and Gonzalo Martínez-Muñoz. 2021. A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review 54 (03 2021). https://doi.org/10.1007/s10462-020-09896-5

Digital Library

[5]

CatBoost. 2021. Transforming categorical features to numerical features. Yandex. https://catboost.ai/docs/concepts/algorithm-main-stages_text-to-numeric.html?lang=en

[6]

Debaditya Chakraborty and Hazem Elzarka. 2018. Performance testing of energy models: are we using the right statistical metrics?Journal of Building Performance Simulation 11, 4 (2018), 433–448. https://doi.org/10.1080/19401493.2017.1387607

[7]

Debaditya Chakraborty and Hazem Elzarka. 2019. Advanced machine learning techniques for building performance simulation: a comparative analysis. Journal of Building Performance Simulation 12, 2 (2019), 193–207. https://doi.org/10.1080/19401493.2018.1498538

[8]

Tianqi Chen and Carlos Guestrin. 2016. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California, USA) (KDD ’16). Association for Computing Machinery, New York, NY, USA, 785––794. https://doi.org/10.1145/2939672.2939785

Digital Library

[9]

Shamit Roy Chowdhury, Sushruta Mishra, Annie Olivia Miranda, and Pradeep Kumar Mallick. 2021. Energy Consumption Prediction Using Light Gradient Boosting Machine Model. Advances in Power Systems and Energy Management Lecture Notes in Electrical Engineering 690 (Jan. 2021), 413–422. https://doi.org/10.1007/978-981-15-7504-4_39

[10]

Hengfang Deng, David Fannon, and Matthew J. Eckelman. 2018. Predictive modeling for US commercial building energy use: A comparison of existing statistical and machine learning algorithms using CBECS microdata. Energy and Buildings 163 (March 2018), 34–43. https://doi.org/10.1016/j.enbuild.2017.12.031

[11]

EnergyPlus. 2021. EnergyPlus | EnergyPlus. https://energyplus.net/

[12]

Cheng Fan, Fu Xiao, and Yang Zhao. 2017. A short-term building cooling load prediction method using deep learning algorithms. Applied Energy 195(2017), 222–233. https://doi.org/10.1016/j.apenergy.2017.03.064

[13]

Jerome H. Friedman. 2002. Stochastic gradient boosting. Computational Statistics & Data Analysis 38, 4 (2002), 367–378. https://doi.org/10.1016/S0167-9473(01)00065-2 Nonlinear Methods and Data Mining.

Digital Library

[14]

Alfonso González-Briones, Guillermo Hernández, Tiago Pinto, Zita Vale, and Juan M. Corchado. 2019. A Review of the Main Machine Learning Methods for Predicting Residential Energy Consumption. In 2019 16th International Conference on the European Energy Market (EEM). IEEE, Ljubljana, Slovenia, 1–6. https://doi.org/10.1109/EEM.2019.8916406

[15]

Monika Goyal, Mrinal Pandey, and Rahul Thakur. 2020. Exploratory Analysis of Machine Learning Techniques to predict Energy Efficiency in Buildings. In 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO). IEEE, Noida, India, 1033–1037. https://doi.org/10.1109/ICRITO48877.2020.9197976

[16]

Jessica Grove-Smith, Vera Aydin, Wolfgang Feist, Jürgen Schnieders, and Stefan Thomas. 2018. Standards and policies for very high energy efficiency in the urban building sector towards reaching the 1.5°C target. Current Opinion in Environmental Sustainability 30 (2018), 103–114. https://doi.org/10.1016/j.cosust.2018.04.006 1.5°C Climate change and urban areas.

[17]

Intergovernmental Panel on Climate Change. 2021. Global Warming of 1.5°C. An IPCC Special Report. Technical Report. United Nations. https://www.ipcc.ch/sr15/chapter/spm/

[18]

Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems 30 (2017), 3146–3154.

Digital Library

[19]

National Renewable Energy Laboratory. 2021. NSRDB Data Viewer. https://maps.nrel.gov/nsrdb-viewer/?aL=x8CI3i%255Bv%255D%3Dt%26Jea8x6%255Bv%255D%3Dt%26Jea8x6%255Bd%255D%3D1%26VRLt_G%255Bv%255D%3Dt%26VRLt_G%255Bd%255D%3D2%26mcQtmw%255Bv%255D%3Dt%26mcQtmw%255Bd%255D%3D3&bL=clight&cE=0&lR=0&mC=4.740675384778373%2C22.8515625&zL=2

[20]

Scikit Learn. 2021. sklearn.model_selection.GridSearchCV. SciKit Learn. https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html

[21]

Pin Li and Jin-Suo Zhang. 2018. A New Hybrid Method for China’s Energy Supply Security Forecasting Based on ARIMA and XGBoost. Energies 11, 7 (2018), 1–28. https://doi.org/10.3390/en11071687

[22]

LightGBM. 2021. Parameters Tuning. Microsoft Corporation. https://lightgbm.readthedocs.io/en/latest/Parameters-Tuning.html

[23]

Hongfang Lu, Feifei Cheng, Xin Ma, and Gang Hu. 2020. Short-term prediction of building energy consumption employing an improved extreme gradient boosting model: A case study of an intake tower. Energy 203(2020), 117756. https://doi.org/10.1016/j.energy.2020.117756

[24]

Clayton Miller, Pandarasamy Arjunan, Anjukan Kathirgamanathan, Chun Fu, Jonathan Roth, June Young Park, Chris Balbach, Krishnan Gowri, Zoltan Nagy, Anthony D. Fontanini, and Jeff Haberl. 2020. The ASHRAE Great Energy Predictor III competition: Overview and results. Science and Technology for the Built Environment 26, 10(2020), 1427–1447. https://doi.org/10.1080/23744731.2020.1795514

[25]

Mobius. 2021. Building Sites Power Consumption | Kaggle. https://www.kaggle.com/arashnic/building-sites-power-consumption-dataset

[26]

Jihoon Moon, Jinwoong Park, Eenjun Hwang, and Sanghoon Jun. 2018. Forecasting power consumption for higher educational institutions based on machine learning. The Journal of Supercomputing 74, 8 (01 Aug. 2018), 3778–3800. https://doi.org/10.1007/s11227-017-2022-x

Digital Library

[27]

National Aeronautics and Space Administration. 2021. Climate Change: How Do We Know?NASA. https://climate.nasa.gov/evidence/

[28]

United States Department of Energy. 2020. Commercial Prototype Building Models | Building Energy Codes Program. https://www.energycodes.gov/development/commercial/prototype_models

[29]

Simona-Vasilica Oprea and Adela Bâra. 2019. Machine Learning Algorithms for Short-Term Load Forecast in Residential Buildings Using Smart Meters, Sensors and Big Data Solutions. IEEE Access 7(2019), 177874–177889. https://doi.org/10.1109/ACCESS.2019.2958383

[30]

Kohei Ozaki. 2020. LightGBM Tuner: New Optuna Integration for Hyperparameter Optimization. Optuna. https://medium.com/optuna/lightgbm-tuner-new-optuna-integration-for-hyperparameter-optimization-8b7095e99258

[31]

Yue Pan and Limao Zhang. 2020. Data-driven estimation of building energy consumption with multi-source heterogeneous data. Applied Energy 268(2020), 114965. https://doi.org/10.1016/j.apenergy.2020.114965

[32]

Nikolaos G. Paterakis, Elena Mocanu, Madeleine Gibescu, Bart Stappers, and Walter van Alst. 2017. Deep learning versus traditional machine learning methods for aggregated energy demand prediction. In 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe). IEEE, Turin, Italy, 1–6. https://doi.org/10.1109/ISGTEurope.2017.8260289

[33]

Peltarion. 2021. Mean squared logarithmic error (MSLE) | Peltarion Platform. https://peltarion.com/knowledge-center/documentation/modeling-view/build-an-ai-model/loss-functions/mean-squared-logarithmic-error-(msle)

[34]

Tiago Pinto, Isabel Praça, Zita Vale, and Jose Silva. 2021. Ensemble learning for electricity consumption forecasting in office buildings. Neurocomputing 423(2021), 747–755. https://doi.org/10.1016/j.neucom.2020.02.124

[35]

Aida Mehdipour Pirbazari, Antorweep Chakravorty, and Chunming Rong. 2019. Evaluating Feature Selection Methods for Short-Term Load Forecasting. In 2019 IEEE International Conference on Big Data and Smart Computing (BigComp). IEEE, Kyoto, Japan, 1–8. https://doi.org/10.1109/BIGCOMP.2019.8679188

[36]

Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna Veronika Dorogush, and Andrey Gulin. 2017. CatBoost: unbiased boosting with categorical features. Technical Report. arXiv. arXiv:arXiv:1706.09516

[37]

Y D Qin, J Ke, and B Wang. 2021. Exploring New Building Energy Saving Control Strategy Application under the Energy Internet of Things. IOP Conference Series: Earth and Environmental Science 701, 1 (March 2021), 012060. https://doi.org/10.1088/1755-1315/701/1/012060

[38]

Muhammad Sajjad, Zulfiqar Ahmad Khan, Amin Ullah, Tanveer Hussain, Waseem Ullah, Mi Young Lee, and Sung Wook Baik. 2020. A Novel CNN-GRU-Based Hybrid Approach for Short-Term Residential Load Forecasting. IEEE Access 8(2020), 143759–143768. https://doi.org/10.1109/ACCESS.2020.3009537

[39]

Saleh Seyedzadeh, Farzad Pour Rahimian, Parag Rastogi, and Ivan Glesk. 2019. Tuning machine learning models for prediction of building energy loads. Sustainable Cities and Society 47 (2019), 101484. https://doi.org/10.1016/j.scs.2019.101484

[40]

United Nations. 2021. The Climate Crisis – A Race We Can Win. United Nations. https://www.un.org/en/un75/climate-crisis-race-we-can-win

[41]

United States Energy Information Administration. 2001. Electric Utility Demand Side Management - Archive. Technical Report. United States Energy Information Administration. https://www.eia.gov/electricity/data/eia861/dsm/

[42]

Ran Wang, Shilei Lu, and Wei Feng. 2020. A novel improved model for building energy consumption prediction based on model integration. Applied Energy 262, 1 (March 2020), 012060. https://doi.org/10.1016/j.apenergy.2020.114561

[43]

Ran Wang, Shilei Lu, and Qiaoping Li. 2019. Multi-criteria comprehensive study on predictive algorithm of hourly heating energy consumption for residential buildings. Sustainable Cities and Society 49 (2019), 101623. https://doi.org/10.1016/j.scs.2019.101623

[44]

Zhe Wang, Tianzhen Hong, and Mary Ann Piette. 2020. Building thermal load prediction through shallow machine learning and deep learning. Applied Energy 263(2020), 114683. https://doi.org/10.1016/j.apenergy.2020.114683

[45]

Hai xiang Zhao and Frédéric Magoulès. 2012. A review on the prediction of building energy consumption. Renewable and Sustainable Energy Reviews 16, 6 (2012), 3586–3592. https://doi.org/10.1016/j.rser.2012.02.049

[46]

Xiaotong Yu, Zhezhuang Xu, Xin Zhou, Jiejun Zheng, Yuxiong Xia, Larry Lin, and Shih-Hau Fang. 2019. Load Forecasting Based on Smart Meter Data and Gradient Boosting Decision Tree. In 2019 Chinese Automation Congress (CAC). IEEE, Hangzhou, China, 4438–4442. https://doi.org/10.1109/CAC48633.2019.8996810

[47]

Wu Yucong and Wang Bo. 2020. Research on EA-Xgboost Hybrid Model for Building Energy Prediction. Journal of Physics: Conference Series 1518 (04 2020), 012082. https://doi.org/10.1088/1742-6596/1518/1/012082

[48]

Wu Yucong and Wang Bo. 2020. Research on EA-Xgboost Hybrid Model for Building Energy Prediction. Journal of Physics: Conference Series 1518 (04 2020), 012082. https://doi.org/10.1088/1742-6596/1518/1/012082

[49]

Liang Zhang, Jin Wen, Yanfei Li, Jianli Chen, Yunyang Ye, Yangyang Fu, and William Livingood. 2021. A review of machine learning in building load prediction. Applied Energy 285(2021), 116452. https://doi.org/10.1016/j.apenergy.2021.116452

[50]

Yong Zhang, Xiaomin Zhou, Yinglei Teng, Jinghui Fang, and Weijun Zheng. 2018. Resource Allocation for Multi-User MEC System: Machine Learning Approaches. In 2018 International Conference on Computational Science and Computational Intelligence (CSCI). IEEE, Las Vegas, NV, USA, 794–799. https://doi.org/10.1109/CSCI46756.2018.00159

[51]

Huiting Zheng, Jiabin Yuan, and Long Chen. 2017. Short-Term Load Forecasting Using EMD-LSTM Neural Networks with a Xgboost Algorithm for Feature Importance Evaluation. Energies 10, 8 (2017), 1–20. https://doi.org/10.3390/en10081168

Cited By

Qu XLiu Z(2024)Forecasting the total building energy based on its architectural features using a combination of CatBoost and meta-heuristic algorithmsEnergy & Environment10.1177/0958305X241241029Online publication date: 3-Apr-2024
https://doi.org/10.1177/0958305X241241029
Oh KKim E(2024)Predicting the energy consumption of a VRF heat pump using manufacturer performance data and limited experimentation for dynamic data collectionEnergy and Buildings10.1016/j.enbuild.2023.113798303(113798)Online publication date: Jan-2024
https://doi.org/10.1016/j.enbuild.2023.113798
Huang YZhao YWang ZLiu XFu Y(2024)Sparse dynamic graph learning for district heat load forecastingApplied Energy10.1016/j.apenergy.2024.123685371(123685)Online publication date: Oct-2024
https://doi.org/10.1016/j.apenergy.2024.123685
Show More Cited By

Index Terms

Building Energy Consumption Forecasting: A Comparison of Gradient Boosting Models

Index terms have been assigned to the content through auto-classification.

Recommendations

A comparative analysis of gradient boosting algorithms
Abstract
The family of gradient boosting algorithms has been recently extended with several interesting proposals (i.e. XGBoost, LightGBM and CatBoost) that focus on both speed and accuracy. XGBoost is a scalable ensemble technique that has demonstrated to ...
Designing and Implementation of Novel Ensemble model based on ANFIS and Gradient Boosting methods for Hand Gestures Classification
SoICT '22: Proceedings of the 11th International Symposium on Information and Communication Technology

Communication through hand gestures has always been the primary method worldwide. There are numerous methods implemented for the classification of hand gestures. However, most successful attempts use Convectional Neural Network (CNN) based methods, ...
Using Automatic Programming to Improve Gradient Boosting for Classification
Artificial Intelligence and Soft Computing
Abstract
In this paper, we present our new and automatically tuned gradient boosting software, Classifium GB, which beats its closest competitor, H2O, for all datasets that we ran. The primary reason that we found it easy to develop Classifium GB is that ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

IAIT '21: Proceedings of the 12th International Conference on Advances in Information Technology

June 2021

281 pages

ISBN:9781450390125

DOI:10.1145/3468784

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 July 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

IAIT2021

IAIT2021: The 12th International Conference on Advances in Information Technology

June 29 - July 1, 2021

Bangkok, Thailand

Acceptance Rates

Overall Acceptance Rate 20 of 47 submissions, 43%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
304
Total Downloads

Downloads (Last 12 months)111
Downloads (Last 6 weeks)22

Reflects downloads up to 15 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Qu XLiu Z(2024)Forecasting the total building energy based on its architectural features using a combination of CatBoost and meta-heuristic algorithmsEnergy & Environment10.1177/0958305X241241029Online publication date: 3-Apr-2024
https://doi.org/10.1177/0958305X241241029
Oh KKim E(2024)Predicting the energy consumption of a VRF heat pump using manufacturer performance data and limited experimentation for dynamic data collectionEnergy and Buildings10.1016/j.enbuild.2023.113798303(113798)Online publication date: Jan-2024
https://doi.org/10.1016/j.enbuild.2023.113798
Huang YZhao YWang ZLiu XFu Y(2024)Sparse dynamic graph learning for district heat load forecastingApplied Energy10.1016/j.apenergy.2024.123685371(123685)Online publication date: Oct-2024
https://doi.org/10.1016/j.apenergy.2024.123685
Singh NFukushima TNagahara M(2023)Gradient Boosting Approach to Predict Energy-Saving Awareness of Households in KitakyushuEnergies10.3390/en1616599816:16(5998)Online publication date: 16-Aug-2023
https://doi.org/10.3390/en16165998
C. DN. WC. C(2023)Forecasting Energy Consumption in the Chimborazo Province, Ecuador, Using Random Forest and XGBoost Algorithms2023 1st International Conference on Advanced Engineering and Technologies (ICONNIC)10.1109/ICONNIC59854.2023.10467276(66-72)Online publication date: 14-Oct-2023
https://doi.org/10.1109/ICONNIC59854.2023.10467276
Al-Areeq AAbba SHalder BAhmadianfar IHeddam SDemir VKilinc HFarooque ATan MYaseen Z(2023)Flood Subsidence Susceptibility Mapping using Elastic-net Classifier: New ApproachWater Resources Management10.1007/s11269-023-03591-037:13(4985-5006)Online publication date: 16-Sep-2023
https://doi.org/10.1007/s11269-023-03591-0
Mariano-Hernández DHernández-Callejo LSolís MZorita-Lamadrid ADuque-Pérez OGonzalez-Morales LGarcía FJaramillo-Duque AOspino-Castro AAlonso-Gómez VBello H(2022)Analysis of the Integration of Drift Detection Methods in Learning Algorithms for Electrical Consumption Forecasting in Smart BuildingsSustainability10.3390/su1410585714:10(5857)Online publication date: 12-May-2022
https://doi.org/10.3390/su14105857
Mariano‐Hernández DHernández‐Callejo LSolís MZorita‐Lamadrid ADuque‐Pérez OGonzalez‐Morales LAlonso‐Gómez VJaramillo‐Duque ASantos García F(2022)Comparative study of continuous hourly energy consumption forecasting strategies with small data sets to support demand management decisions in buildingsEnergy Science & Engineering10.1002/ese3.129810:12(4694-4707)Online publication date: 2-Sep-2022
https://doi.org/10.1002/ese3.1298
Kim JLee JPark M(2021)Analysis of Lifelong for Health of Middle-Aged Men by Using Machine Learning AlgorithmJournal of the Korean Institute of Industrial Engineers10.7232/JKIIE.2021.47.6.50447:6(504-513)Online publication date: 15-Dec-2021
https://doi.org/10.7232/JKIIE.2021.47.6.504

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents