Predicting Energy Consumption of Office Buildings: A Hybrid Machine Learning-Based Approach

  • Kadir Amasyali
  • Nora El-GoharyEmail author
Conference paper


Improving building energy efficiency requires an understanding of the affecting factors and an assessment of different design and operation alternatives. In this context, accurate prediction of building energy consumption gained a lot of research attention. In recent years, a significant number of building energy consumption prediction models, with various intended uses, have been proposed. However, existing data-driven models are mostly based on outdoor weather conditions, but do not take occupant behavior into account. Towards addressing this research gap, this paper presents a hybrid machine-learning and data-mining approach to develop prediction models that learn from both real data and simulation-generated data. Real data were collected from an office building, including data about building energy consumption, outdoor weather conditions, and occupant behavior. Simulation-generated data were created through simulating an office building in EnergyPlus. A feature selection algorithm was used to determine the critical features in predicting energy consumption for office buildings. A set of regression models were then trained for predicting the hourly values of an outdoor weather-related factor and an occupant behavior-related factor based on these features. Then, an ensembler model—which takes the outputs of the outdoor weather-related factor and occupant behavior-related factor models—was trained to predict cooling energy consumption. In training the models, several machine learning algorithms—such as Gaussian Process Regression (GPR), Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Linear Regression (LR)—were tested. The predicted energy consumption levels showed agreement with the actual levels. This indicates that the proposed regression models can help support decision making related to office buildings.


Building energy efficiency Energy consumption prediction Machine learning 



This publication was made possible by NPRP Grant #6-1370-2-552 from the Qatar National Research Fund (a member of Qatar Foundation). The findings achieved herein are solely the responsibility of the authors. The authors would like to thank the Philadelphia Business and Technology Center (PBTC) and the Penn State Consortium for Building Energy Innovation (CBEI) for providing access to building energy data, and Prof. Chimay Anumba and Yewande Abraham for helping the authors with the data collection.


  1. 1.
    Zhao, Z., Amasyali, K., Chamoun, R., El-Gohary, N.: Occupants’ Perceptions about Indoor Environment Comfort and Energy Related Values in Commercial and Residential Buildings. Procedia Environ. Sci. 34, 631–640 (2016). CrossRefGoogle Scholar
  2. 2.
    Klein, L., Kwak, J., Kavulya, G., Jazizadeh, F., Becerik-Gerber, B., Varakantham, P., Tambe, M.: Coordinating occupant behavior for building energy and comfort management using multi-agent systems. Autom. Constr. 22, 525–536 (2012). CrossRefGoogle Scholar
  3. 3.
    Clevenger, C.M., Haymaker, J.R., Jalili, M.: Demonstrating the impact of the occupant on building performance. J. Comput. Civ. Eng. 28, 99–102 (2014). CrossRefGoogle Scholar
  4. 4.
    Azar, E., Menassa, C.C.: A comprehensive analysis of the impact of occupancy parameters in energy simulation of office buildings. Energy Build. 55, 841–853 (2012). CrossRefGoogle Scholar
  5. 5.
    Petersen, J.E., Shunturov, V., Janda, K., Platt, G., Weinberger, K.: Dormitory residents reduce electricity consumption when exposed to real-time visual feedback and incentives. Int. J. Sustain. High. Educ. 8, 16–33 (2007). CrossRefGoogle Scholar
  6. 6.
    Delmas, M.A., Fischlein, M., Asensio, O.I.: Information strategies and energy conservation behavior: a meta-analysis of experimental studies from 1975 to 2012. Energy Policy. 61, 729–739 (2013). CrossRefGoogle Scholar
  7. 7.
    Jain, R.K., Taylor, J.E., Culligan, P.J.: Investigating the impact eco-feedback information representation has on building occupant energy consumption behavior and savings. Energy Build. 64, 408–414 (2013). CrossRefGoogle Scholar
  8. 8.
    Li, Z., Huang, G.: Re-evaluation of building cooling load prediction models for use in humid subtropical area. Energy Build. 62, 442–449 (2013). CrossRefGoogle Scholar
  9. 9.
    Wang, Z., Wang, Y., Zeng, R., Srinivasan, R.S., Ahrentzen, S.: Random forest based hourly building energy prediction. Energy Build. (2018). CrossRefGoogle Scholar
  10. 10.
    O’Brien, W., Gunay, H.B.: Mitigating office performance uncertainty of occupant use of window blinds and lighting using robust design. Build. Simul. 8, 621–636 (2015). CrossRefGoogle Scholar
  11. 11.
    Yousefi, F., Gholipour, Y., Yan, W.: A study of the impact of occupant behaviors on energy performance of building envelopes using occupants’ data. Energy Build. 148, 182–198 (2017). CrossRefGoogle Scholar
  12. 12.
    CBEI: Consortium for Building Energy Innovation, Accessed 26 Apr 2018
  13. 13.
    Pennsylvania State Climatologist: Pennsylvania State Climatologist, Accessed 26 Apr 2018
  14. 14.
    Abraham, Y., Zhao, Z., Anumba, C., Asadi, S.: Implementation of a preference monitoring application for office building occupants. In: Lean and Computing in Construction Congress—Volume 1: Proceedings of the Joint Conference on Computing in Construction, pp. 793–801. Heriot-Watt University, Heraklion (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of Illinois at Urbana-ChampaignUrbanaUSA

Personalised recommendations