Computer Science - Research and Development

, Volume 33, Issue 1–2, pp 105–115 | Cite as

PROMT: predicting occupancy presence in multiple resolution with time-shift agnostic classification

  • Fisayo Caleb SangogboyeEmail author
  • Mikkel Baun Kjærgaard
Special Issue Paper


Improving methods for predicting occupant presence in commercial buildings is crucial for optimizing energy consumption. Also it is crucial for providing amiable indoor environmental conditions. To enable these improvements, we require a more accurate and flexible framework for predicting occupancy. The promt framework proposed in this paper is an accurate and flexible framework for predicting occupancy presence in multiple resolution with time-shift agnostic classification. promt assumes that no single prediction algorithm, model, or static model parameter can guarantee high fidelity occupancy prediction for varying occupancy requirements and for every kind of rooms. Given this assumption, the promt framework facilitates the deployment of several prediction algorithms and it performs an hyper-parameter optimization procedure on all deployed algorithms to obtain the optimal model for obtaining occupancy prediction in covered room. promt was benchmarked with datasets from two building cases by comparing the F-score of the prediction results obtained from all deployed algorithms. The results document that promt outperforms the performance of any single prediction algorithm by a maximum difference in F-score of 2.3% and a minimum difference in F-score of 0.58%. As a case study we demonstrate the use of promt for scheduling demand response events in a commercial building.


Occupancy framework Presence prediction Energy savings Demand response 



This work is supported by EUDP for the Project Demand-Response Capacity Management in Commercial Buildings (64014-0512) and Innovation Fund Denmark for COORDICY (4106-00003B).


  1. 1.
    Arendt K, Ionesi A, Jradi M, Singh A, Kjærgaard M, Veje C, Jørgensen B (2016) A building model framework for a genetic algorithm multi-objective model predictive control. In: CLIMA 2016Google Scholar
  2. 2.
    Beltran A, Cerpa AE (2014) Optimal HVAC building control with occupancy prediction. In: BuildSys’14, pp 168–171Google Scholar
  3. 3.
    Dawson-Haggerty S, Jiang X, Tolle G, Ortiz J, Culler D (2010) sMAP: a simple measurement and actuation profile for physical information. In: SenSys. ACM, pp 197–210Google Scholar
  4. 4.
    Erickson V, Carreira-Perpinan MA, Cerpa AE (2011) OBSERVE: occupancy-based system for efficient reduction of HVAC energy. IPSN 2011:258–269Google Scholar
  5. 5.
    Forman G, Scholz M (2010) Apples-to-apples in cross-validation studies: pitfalls in classifier performance measurement. SIGKDD Explor Newsl 12(1):49–57CrossRefGoogle Scholar
  6. 6.
    Kjærgaard MB, Johansen A, Sangogboye FC, Holmegaard E (2016) Occure: an occupancy reasoning platform for occupancy-driven applications. In: CBSE. ACMGoogle Scholar
  7. 7.
    Kjærgaard MB, Sangogboye FC (2017) Categorization framework and survey of occupancy sensing systems. Pervasive Mob Comput 38:1–13Google Scholar
  8. 8.
    Koehler C, Banovic N, Oakley I, Mankoff J, Dey AK (2014) Indoor-alps: an adaptive indoor location prediction system. In: UbiComp, pp 171–181Google Scholar
  9. 9.
    Koehler C, Ziebart BD, Mankoff J, Dey AK (2013) Therml: occupancy prediction for thermostat control. In: UbiComp, pp 103–112Google Scholar
  10. 10.
    McKinney W (2011) pandas: a foundational Python library for data analysis and statistics. In: PyHPC 2011: Workshop on Python for High Performance and Scientific Computing, SC11, Seattle, WA, USA, pp 1–9Google Scholar
  11. 11.
    Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. JMLR 12:2825–2830MathSciNetzbMATHGoogle Scholar
  12. 12.
    Sakoe H, Chiba S (1978) Dynamic programming algorithm optimization for spoken word recognition. IEEE TASSP 26(1):43–49CrossRefzbMATHGoogle Scholar
  13. 13.
    Sangoboye FC, Kjærgaard MB (2016) Predicting occupancy presence in multiple resolutions for commercial buildings: poster abstract. In: Proceedings of the 3rd ACM international conference on systems for energy-efficient built environments, BuildSys’16, New York, NY, ACM, pp 229–230Google Scholar
  14. 14.
    Sangogboye FC, Arendt K, Singh A, Veje CT, Kjærgaard MB, Jørgensen BN (2017) Performance comparison of occupancy count estimation and prediction with common versus dedicated sensors for building model predictive control. Build Simul. doi: 10.1007/s12273-017-0397-5
  15. 15.
    Sangogboye FC, Imamovic K, Kjaergaard MB (2016) Improving occupancy presence prediction via multi-label classification. In: PerEnergy 2016. IEEEGoogle Scholar
  16. 16.
    Scott J, Brush AJB, Krumm J, Meyers B, Hazas M, Hodges S, Villar N (2011) Preheat: controlling home heating using occupancy prediction. UbiComp 2011:281–290Google Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  • Fisayo Caleb Sangogboye
    • 1
    Email author
  • Mikkel Baun Kjærgaard
    • 1
  1. 1.SDU Center for Energy Informatics, Mærsk McKinney Møller InstituteUniversity of Southern DenmarkOdenseDenmark

Personalised recommendations