Environment Systems and Decisions

, Volume 39, Issue 3, pp 281–294 | Cite as

Data-driven simulation for energy consumption estimation in a smart home

  • Stephen AdamsEmail author
  • Steven Greenspan
  • Maria Velez-Rojas
  • Serge Mankovski
  • Peter A. Beling


Simulation and data-driven models are both tools that can play an important role in reducing the energy consumption of buildings and homes. However, sophisticated control schemes and models are only as good as the data collected by sensors and provided to them. Low-quality or faulty sensor that provide inaccurate data can lead to inefficient buildings. In this paper, we investigate the relationship between sensor quality and the prediction of energy consumption. We first construct a simulation of appliance energy consumption in a smart home and then assess the predictive ability of several data-driven models while varying the quality and function of the simulated sensors. The simulation was constructed using a smart home data set collected by other researchers. We find that the predictive ability is only decreased when noise is added to the appliance energy random variable. We conclude that low-quality sensors that do not monitor the environment as accurately as the devices used in the original study could be used for humidity and temperature without significantly reducing the predictive ability of the data-driven models. The method and findings have implications for how to conduct cost-benefit analyses of IoT device requirements.


Data-driven models Energy estimation Simulation 



Temperature parameter for Boltzman distribution of light energy consumption


Temperature parameter for Boltzman distribution of appliance energy consumption


Gradient boosted machines


Heating, ventilation, and air conditioning




Mean absolute error


Mean absolute percentage error


Mean of Gaussian distribution


Relative humidity sensor number #


Root mean squared error


Standard deviation of Gaussian distribution


Support vector machine


Temperature sensor number #


Random variable for appliance energy consumption



This material is based upon work supported by the National Science Foundation under Grant No. CNS: 1650512. This work was conducted in the NSF UICRC Center of Visual and Decision Dynamics, through the sponsorship and guidance of CA Technologies. We thank people on the team who choose not be authors for their thoughts on this paper and the overall project.


  1. Ahmad MW, Mourshed M, Yuce B, Rezgui Y (2016) Computational intelligence techniques for HVAC systems: a review. Build Simul 9(4):359–398Google Scholar
  2. Allard I, Olofsson T, Nair G (2018) Energy evaluation of residential buildings: performance gap analysis incorporating uncertainties in the evaluation methods. Build Simul 11(4):725–737Google Scholar
  3. Alliance Z (2006) Zigbee specificationGoogle Scholar
  4. Barbato A, Capone A, Rodolfi M, Tagliaferri D (2011) Forecasting the usage of household appliances through power meter sensors for demand management in the smart grid. In: 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm)Google Scholar
  5. Belafi Z, Hong T, Reith A (2017) Smart building management vs intuitive human controllessons learnt from an office building in Hungary. Build Simul 10(6):811–828Google Scholar
  6. Breiman L (2001) Random forests. Machin Learn 45(1):5–32Google Scholar
  7. Candanedo LM, Feldheim V, Deramaix D (2017) Data driven prediction models of energy use of appliances in a low-energy house. Energy Build 140:81–97Google Scholar
  8. Cetin K, Tabares-Velasco P, Novoselac A (2014) Appliance daily energy use in new residential buildings: use profiles and variation in time-of-use. Energy Build 84:716–726Google Scholar
  9. Chen J, Ma J, Lo S (2017) Event-driven modeling of elevator assisted evacuation in ultra high-rise buildings. Simul Model Pract Theory 74:99–116Google Scholar
  10. Chen Y, Hong T, Luo X (2018) An agent-based stochastic occupancy simulator. Build Simul 11(1):37–49Google Scholar
  11. Costa A, Keane MM, Torrens JI, Corry E (2013) Building operation and energy performance: monitoring, analysis and optimisation toolkit. Appl Energy 101:310–316Google Scholar
  12. Ding Y, Yang L, Weng F, Fu Z, Rao P (2015) Investigation of combined stairs elevators evacuation strategies for high rise buildings based on simulation. Simul Model Pract Theory 53:60–73Google Scholar
  13. D'Oca S, Fabi V, Corgnati SP, Andersen RK (2014) Effect of thermostat and window opening occupant behavior models on energy use in homes. Build Simul 7(6):683–694Google Scholar
  14. Dong B, Cao C, Lee SE (2005) Applying support vector machines to predict building energy consumption in tropical region. Energy Build 37(5):545–553Google Scholar
  15. Draper NR, Smith H (2014) Applied regression analysis. Wiley, HobokenGoogle Scholar
  16. Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232Google Scholar
  17. Hong T, Langevin J, Sun K (2018) Building simulation: ten challenges. Build Simul 11:1–18Google Scholar
  18. Johnson G, Beausoleil-Morrison I (2017) Electrical-end-use data from 23 houses sampled each minute for simulating micro-generation systems. Appl Therm Eng 114:1449–1456Google Scholar
  19. Kavousian A, Rajagopal R, Fischer M (2015) Ranking appliance energy efficiency in households: Utilizing smart meter data and energy efficiency frontiers to estimate and identify the determinants of appliance energy efficiency in residential buildings. Energy Build 99:220–230Google Scholar
  20. Lichman M (2013) UCI machine learning repository. UNiversity of California, IrvineGoogle Scholar
  21. Marchese D, Linkov I (2017) Can you be smart and resilient at the same time? Environ Sci Technol 51(11):5867–5868Google Scholar
  22. Mirakhorli A, Dong B (2017) Occupant-behavior driven appliance scheduling for residential buildings. BUild Simul 10(6):917–931Google Scholar
  23. Muratori M, Roberts MC, Sioshansi R, Marano V, Rizzoni G (2013) A highly resolved modeling technique to simulate residential power demand. Appl Energy 107:465–473Google Scholar
  24. Murphy KP (2012) Machine learning: a probabilistic perspective. MIT press, CambridgeGoogle Scholar
  25. R Core Team (2013) R: a language and environment for statistical computing. R Foundation for Statistical Computing, ViennaGoogle Scholar
  26. Ruellan M, Park H, Bennacer R (2016) Residential building energy demand and thermal comfort: thermal dynamics of electrical appliances and their impact. Energy Build 130:46–54Google Scholar
  27. Sano T, Ronchi E, Minegishi Y, Nilsson D (2018) Modelling pedestrian merging in stair evacuation in multi-purpose buildings. Simul Model Pract Theory 85:80–94Google Scholar
  28. Seem JE (2007) Using intelligent data analysis to detect abnormal energy consumption in buildings. Energy Build 39(1):52–58Google Scholar
  29. Shaikh PH, Nor NBM, Nallagownden P, Elamvazuthi I, Ibrahim T (2014) A review on optimized control systems for building energy and comfort management of smart sustainable buildings. Renew Sustain Energy Rev 34:409–429Google Scholar
  30. Trčka M, Hensen JL, Wetter M (2010) Co-simulation for performance prediction of integrated building and HVAC systems-an analysis of solution characteristics using a two-body system. Simul Model Pract Theory 18(7):957–970Google Scholar
  31. Wang C, Yan D, Jiang Y (2011) A novel approach for building occupancy simulation. Build Simul 4(2):149–167Google Scholar
  32. Xue P, Hong T, Dong B, Mak C (2017) A preliminary investigation of water usage behavior in single-family homes. Build Simul 10(6):949–962Google Scholar
  33. Yang Z, Li N, Becerik-Gerber B, Orosz M (2014) A systematic approach to occupancy modeling in ambient sensor-rich buildings. Simulation 90(8):960–977Google Scholar
  34. Zhao P, Suryanarayanan S, Simões MG (2013) An energy management system for building structures using a multi-agent decision-making control methodology. IEEE Trans Ind Appl 49(1):322–330Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.University of VirginiaCharlottesvilleUSA
  2. 2.CA TechnologiesEwingUSA
  3. 3.CA TechnologiesSanta ClaraUSA

Personalised recommendations