Skip to main content
SpringerLink
Log in

Using the Instance-Based Learning Paradigm to Model Energy-Relevant Occupant Behaviors in Buildings

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Human interactive behavior is accountable for most of the variance between the observed and predicted energy consumption of buildings, and is accordingly acknowledged as a major field of research into limiting building-related energy consumption. A thorough understanding of occupant behavior is critical to facilitate a more reliable prediction of energy consumption and identifying means by which pro-environmental behaviors can be promoted. Insights and models from psychology and sociology appear to be best suited to improving such understanding, and this article contributes to this end by developing and testing a cognitive model that serves as the core of a numerical human-building interaction model. The proposed implementation builds on instance-based learning, a well-established cognitive modeling paradigm, is integrated into a thermodynamic building model, and complemented by perception models for the approximation of the thermal and olfactory perception of the environment. The model successfully learns to interact plausibly with a set of elements of a model room—a heating system, a window, and the actor’s clothing—in order to establish predefined room conditions. Accumulation of context-specific instances in the declarative memory, which are retrieved and blended in a decision situation, provide the model with the flexibility to adapt its actions to very different climatic contexts, represented by the locations Stuttgart, Madrid, Stockholm, and Melbourne. Moreover, the model manages to find appropriate compromises if need satisfaction requires contradictory actions, such as in situations where satisfaction of the olfactory need requires opening the window and satisfaction of the thermal need requires keeping it closed. Despite its obvious complexity, the model must be considered to be a basic model, which restricts the immediate comparability of its results to human behavior data. However, the successfully applied plausibility checks clearly indicate the value of the cognitive approach to modeling human-building interaction.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Abbreviations

A:

Total activation

a:

Total number of available actions

Act:

Total action space

B:

Base level activation

BCB:

Blended cost and benefits of an action

BV:

Blended value of an action

C:

Costs associated with an action

CB:

Costs and Benefits of an instance

clo:

Clothing value

d:

Decay factor

fan:

Number of associations between source slot and slots in memory

G:

Ultimate goal of the model

met:

Metabolic rate

N:

Noise activation

n:

Number of needs

o:

Number of occurrences

P:

Probability of retrieval of an instance

PM:

Penalization of activation due to partial matching

pm:

Partial matching scaling parameter

PT:

Perception threshold

R:

Result stored to an instance

r:

Total number of instances (belonging to an action)

s:

Total number of slots of an instance

S:

Associative strength (w/o index: maximum associative strength)

SA:

Spreading activation

SG:

Sub-goal

sim:

Similarity parameter for slot comparison

SR:

Sensation rating

t:

Time

U:

Utility of an instance

W:

Spreading weight

γ:

Random draw out of [0,1]

σ:

Noise scaling parameter

τ:

Imprecision of retrieval (temperature parameter)

adm:

Admissibility

adm:

state State-related admissibility

adm:

switch Switch-related admissibility

clo:

Clothing

curr:

Current

dim:

Dimension to which an action belongs

h:

hth need

heat:

Heating

i, j:

ith and jth instance belonging to action m or m* and need h

k:

kth instance belonging to need h, irrespective of action m

l:

lth slot of an instance

lk:

Between slot l and instance k

m:

mth action

olf:

Olfactory

oper:

Operability

p:

pth occurrence of an instance in the past

relN:

Currently relevant need

state:

State of an action

state x – state y:

Change of states, from state x to state y

therm:

Thermal

tot:

Total

wind:

Window

*:

Considered worthwhile based on the blended value

′:

Cost-penalized

′′:

Costs/benefits-modified

References

  1. UNEP. 2016 [[Accessed 21.8. 2017]. Available from: http://web.unep.org/10yfp/programmes/sustainable-buildings-and-construction-programme.

  2. UNFCCC. Report of the conference of the parties on its sixteenth session, held in Cancun from 29 November to 10 December 2010. 2011.

  3. Andersen RK, editor The influence of occupants’ behaviour on energy consumption investigated in 290 identical dwellings and in 35 apartments. 10th International conference on healthy buildings; 2012; Brisbane.

  4. Ahn K, Park C. Correlation between occupants and energy consumption. Energy and Buildings. 2016;116:420–33.

    Google Scholar 

  5. Janda KB. Buildings don't use energy: people do. Archit Sci Rev. 2011;54(1):15–22.

    Google Scholar 

  6. Meier A, Aragon C, Hurwitz B, Mujumdar D, Peffer H, Perry D, et al. How people actually use thermostats. ACEEE summer study on energy efficiency in buildings Pacific grove. American Council for an Energy Efficient Economy: Calif; 2012.

    Google Scholar 

  7. Branco G, Lachal B, Gallinelli P, Weber W. Predicted versus observed heat consumption of a low energy multifamily complex in Switzerland based on long-term experimental data. Energy and Buildings. 2004;36(6):543–55.

    Google Scholar 

  8. Santin OG, Itard L, Visscher H. The effect of occupancy and building characteristics on energy use for space and water heating in Dutch residential stock. Energy and Buildings. 2009;41(11):1223–32.

    Google Scholar 

  9. Annex_66. Definition and Simulation of Occupant Behavior in Buildings 2018 [[accessed 16.1. 2017]. Available from: https://www.annex66.org/.

  10. Nicol JF. Characterising occupant behaviour in buildings: towards a stochastic model of occupant use of windows, lights, blinds, heaters and fans. Seventh International IBPSA Conference; Rio de Janeiro2001. p. 1073–8.

  11. Newsham GR. Manual control of window blinds and electric lighting: implications for comfort and energy consumption. Indoor and Built Environment. 1994;3(3):135–44.

    Google Scholar 

  12. Rijal HB, Tuohy P, Humphreys MA, Nicol JF, Samuel A. Considering the impact of situation-specific motivations and constraints in the design of naturally ventilated and hybrid buildings. Archit Sci Rev. 2012;55(1):35–48.

    Google Scholar 

  13. Haldi F, Robinson D. Interactions with window openings by office occupants. Build Environ. 2009;44(12):2378–95.

    Google Scholar 

  14. Rijal HB, Tuohy P, Humphreys MA, Nicol JF, Samuel A, Clarke J. Using results from field surveys to predict the effect of open windows on thermal comfort and energy use in buildings. Energy Buildings. 2007;39(7):823–36.

    Google Scholar 

  15. Haldi F, Robinson D. On the behaviour and adaptation of office occupants. Build Environ. 2008;43(12):2163–77.

    Google Scholar 

  16. Rijal HB, Tuohy PG, Nicol JF, Humphreys MA, Samuel A, Raja IA, et al. Development of adaptive algorithms for the operation of windows, fans and doors to predict thermal comfort and energy use in Pakistani buildings. ASHRAE Trans. 2008;114(2):555–73.

    Google Scholar 

  17. Inkarojrit V, Paliaga G, (ed). Indoor climatic influences on the operation of windows in a naturally ventilated building. Proceedings of the 21st international conference on passive and low energy architecture; 2004; Eindhoven, The Netherlands.

  18. Zhang Y, Barrett P. Factors influencing occupants’ blind-control behaviour in a naturally ventilated office building. Build Environ. 2012;54:137–47.

    Google Scholar 

  19. Foster M, Oreszczyn T. Occupant control of passive systems: the use of venetian blinds. Build Environ. 2001;36(2):149–55.

    Google Scholar 

  20. Zhang Y, Barrett P. Factors influencing the occupants’ window opening behaviour in a naturally ventilated office building. Build Environ. 2012;50:125–34.

    CAS  Google Scholar 

  21. Haldi F, Robinson D. Modelling occupants’ personal characteristics for thermal comfort prediction. Int J Biometeorol. 2011;55(5):681–94.

    PubMed  Google Scholar 

  22. Clarke JA, Macdonald I, Nicol JF. Predicting adaptive responses-simulating occupied environments. In: Proceedings of International Conference on Comfort and Energy Use in Buildings; Windsor, England, 2006.

  23. Widén J, Nilsson AM, Wäckelgård E. A combined Markov-chain and bottom-up approach to modelling of domestic lighting demand. Energy Buildings. 2009;41(10):1001–12.

    Google Scholar 

  24. Li N, Li J, Fan R, Jia H. Probability of occupant operation of windows during transition seasons in office buildings. Renew Energy. 2015;73:84–91.

    Google Scholar 

  25. Wang C, Yan D, Sun H, Jiang Y. A generalized probabilistic formula relating occupant behavior to environmental conditions. Build Environ. 2016;95:53–62.

    Google Scholar 

  26. Ren X, Yan D, Wang C. Air-conditioning usage conditional probability model for residential buildings. Build Environ. 2014;81:172–82.

    Google Scholar 

  27. D'Oca S, Gunay HB, Gilani S, O'Brien W. Critical review and illustrative examples of office occupant modelling formalisms. Building Services Engineering Research and Technology. 2019; published online: February 6, 2019.

  28. Wei Y, Yu H, Pan S, Xia L, Xie J, Wang X, et al. Comparison of different window behavior modeling approaches during transition season in Beijing, China. Building and Environment. 2019;157:1–15.

    Google Scholar 

  29. Markovic R, Grintal E, Wölki D, Frisch J, van Treeck C. Window opening model using deep learning methods. Build Environ. 2018;145:319–29.

    Google Scholar 

  30. Belafi ZD, Hong T, Reith A. A library of building occupant behaviour models represented in a standardised schema. Energy Efficiency. 2019;12(3):637–51.

    Google Scholar 

  31. Xu X, Wang W, Hong T, Fu X. Buildings. Occupants: a modelica package for modeling occupant behavior in buildings. J Build Perform Simul 2018;12(4):433–44.

  32. Gunay HB, O'Brien W, Beausoleil-Morrison I. A critical review of observation studies, modeling, and simulation of adaptive occupant behaviors in offices. Build Environ. 2013;70:31–47.

    Google Scholar 

  33. Stazi F, Naspi F. Modelling, Implementation and Validation Approaches. Impact of Occupants' Behaviour on Zero-Energy Buildings. Cham: Springer International Publishing; 2018. p. 63–77.

    Google Scholar 

  34. Kim D-W, Kim J-H, Park S-L, Kim K-C, Park C-S, editors. Traditional vs. cognitive agent simulation. 13th International conference of the international building performance simulation association; 2013.

  35. Langevin J, Wen J, Gurian PL. Simulating the human-building interaction: development and validation of an agent-based model of office occupant behaviors. Build Environ. 2015;88:27–45.

    Google Scholar 

  36. Lee YS, Malkawi AM. Simulating multiple occupant behaviors in buildings: an agent-based modeling approach. Energy and Buildings. 2014;69:407–16.

    Google Scholar 

  37. Yan D, O’Brien W, Hong T, Feng X, Gunay HB, Tahmasebi F, et al. Occupant behavior modeling for building performance simulation: current state and future challenges. Energy Buildings. 2015;107:264–78.

    Google Scholar 

  38. Hong T, Yan D, D'Oca S, Chen C. Ten questions concerning occupant behavior in buildings: the big picture. Build Environ. 2017;114:518–30.

    Google Scholar 

  39. Hong T, Taylor-Lange S, D’Oca S, Yan D, Corgnati S. Advances in research and applications of energy-related occupant behavior in buildings. Energy Buildings. 2016;116:694–702.

    Google Scholar 

  40. Wolf S, Schweiker M, Wagner A, van Treeck C. Revisiting validation methods of occupant behaviour models. In: Proceedings of Healthy Buildings Europe; Eindhoven, The Netherlands 2015.

  41. Ajzen I. The theory of planned behavior. Organ Behav Hum Decis Process. 1991;50(2):179–211.

    Google Scholar 

  42. Ajzen I, Fishbein M. The influence of attitudes on behavior. In: Albarracín D, Johnson BT, Zanna MP, editors. The handbook of Attitudes. Mahwah, NJ: Erlbaum 2005;. p. 173–221.

  43. Zhang T, Zhang D. Agent-based simulation of consumer purchase decision-making and the decoy effect. J Bus Res. 2007;60(8):912–22.

    Google Scholar 

  44. Jager W, Janssen MA, De Vries HJM, De Greef J, Vlek CAJ. Behaviour in commons dilemmas: Homo economicus and Homo psychologicus in an ecological-economic model. Ecol Econ. 2000;35(3):357–79.

    Google Scholar 

  45. Jager W, Mosler HJ. Simulating human behavior for understanding and managing environmental resource use. J Soc Issues. 2007;63(1):97–116.

    Google Scholar 

  46. Scalco A, Ceschi A, Shiboub I, Sartori R, Frayret J-M, Dickert S. The implementation of the theory of planned behavior in an agent-based model for waste recycling: a review and a proposal. In: Alonso-Betanzos A, Sánchez-Maroño N, Fontenla-Romero O, Polhill JG, Craig T, Bajo J, et al. eds. Agent-based modeling of sustainable behaviors. Cham: Springer International Publishing 2017; p. 77–97

    Google Scholar 

  47. García-Mira R, Dumitru A, Alonso-Betanzos A, Sánchez-Maroño N, Fontenla-Romero Ó, Craig T, et al. Testing scenarios to achieve workplace sustainability goals using backcasting and agent-based modeling. Environ Behav 2016;49(9):1007-37.

    Google Scholar 

  48. Sánchez-Maroño N, Alonso-Betanzos A, Fontenla-Romero O, Brinquis-Núñez C, Polhill JG, Craig T, et al. An agent-based model for simulating environmental behavior in an educational organization. Neural Process Lett. 2015;42(1):89–118.

    Google Scholar 

  49. Wunder M, Suri S, Watts DJ. Empirical agent based models of cooperation in public goods games. Proceedings of the fourteenth ACM conference on electronic commerce; Philadelphia, Pennsylvania, USA ACM 2013; p. 891–908.

  50. Kaminski G. Überlegungen zur Funktion von Handlungstheorien in der Psychologie. In: Lenk H, editor. Handlungstheorien–interdisziplinär Bd 3. München: Fink; 1981. p. 93–122.

    Google Scholar 

  51. Miller GA, Galanter E, Pribram KH. Plans and the structure of behavior. New York: Holt, Reinhart and Winston, Inc.; 1960.

    Google Scholar 

  52. Brandtstädter J. Action perspectives on human development. In: Damon W, Lerner RM, eds. Handbook of child psychology: theoretical models of human development. Hoboken: John Wiley & Sons, Inc. 1998; p. 807–63.

  53. Cranach M, Harré R. The analysis of action: recent theoretical and empirical advances, Cambridge: Cambridge University Press; 1982.

  54. Grabe JV. How do occupants decide their interactions with the building? From qualitative data to a psychological framework of human-building-interaction. Energy Res Soc Sci. 2016;14:46–60.

    Google Scholar 

  55. Gonzalez C, Lerch JF, Lebiere C. Instance-based learning in dynamic decision making. Cogn Sci. 2003;27(4):591–635.

    Google Scholar 

  56. Logan GD. Toward an instance theory of automatization. Psychol Rev. 1988;95(4):492–527.

    Google Scholar 

  57. Grabe JV. The systematic identification and organization of the context of energy-relevant human interaction with buildings—a pilot study in Germany. Energy Res Soc Sci. 2016;12:75–95.

    Google Scholar 

  58. Anderson JR, Bothell D, Byrne MD, Douglass S, Lebiere C, Qin Y. An integrated theory of the mind. Psychol Rev. 2004;111(4):1036–60.

    PubMed  Google Scholar 

  59. Dutt V, Ahn YS, Gonzalez C. Cyber situation awareness: modeling detection of cyber attacks with instance-based learning theory. Hum Factors. 2013;55(3):605–18.

    PubMed  Google Scholar 

  60. Dutt V, Cassenti DN, Gonzalez C, editors. Modeling a robotics operator manager in a tactical battlefield. Cognitive Methods in Situation Awareness and Decision Support (CogSIMA), 2011 IEEE First International Multi-Disciplinary Conference on; 2011: IEEE.

  61. Gonzalez C, Dutt V, Lejarraga T. A loser can be a winner: comparison of two instance-based learning models in a market entry competition. Games. 2011;2(1):136–62.

    Google Scholar 

  62. Lebiere C, Gonzalez C, Martin MK. Instance-based decision making model of repeated binary choice. Proceedings of the 8th International Conference on Cognitive Modeling; Ann Abor, Michigan, USA 2007.

  63. Martin MK, Gonzalez C, Lebiere C. Learning to make decisions in dynamic environments: ACT-R plays the beer game. Proceedings of the Sixth International Conference on Cognitive Modeling; Pittsburgh, PA, USA 2004; p. 178–83.

  64. Grabe JV, Gonzalez C. Human decision making in energy-relevant interaction with buildings. Dresden: Central European Symposium on Building Physics, CESBP; 2016. p. 345–52.

    Google Scholar 

  65. Grabe JV. A preliminary cognitive model for the prediction of energy-relevant human interaction with buildings. Cogn Syst Res. 2018;49:65–82.

    Google Scholar 

  66. Sun R. Motivational representations within a computational cognitive architecture. Cogn Comput. 2009;1(1):91–103.

    Google Scholar 

  67. Lebiere C. Blending: an ACT-R mechanism for aggregate retrievals. Proceedings of the Sixth Annual ACT-R Workshop at George Mason University; Fairfax, VA, USA 1999.

  68. Lejarraga T, Dutt V, Gonzalez C. Instance-based learning: a general model of repeated binary choice. J Behav Decis Mak. 2010;25(2):143–53.

    Google Scholar 

  69. Gonzalez C, Dutt V. Instance-based learning: integrating sampling and repeated decisions from experience. Psychol Rev. 2011;118(4):523–51.

    PubMed  Google Scholar 

  70. Dutt V, Gonzalez C. Making instance-based learning theory usable and understandable: the instance-based learning tool. Comput Hum Behav. 2012;28(4):1227–40.

    Google Scholar 

  71. Tversky A, Kahneman D. Judgment under uncertainty: heuristics and biases. Science. 1975;185:1124–31.

    CAS  PubMed  Google Scholar 

  72. Endrejat PC, Baumgarten F, Kauffeld S. When theory meets practice: combining Lewin’s ideas about change with motivational interviewing to increase energy-saving behaviours within organizations. J Chang Manag. 2017:1–20.

  73. Klein A, Beckman A, Mitchell W, Duffie A. TRNSYS 17–a transient system simulation program Madison: Solar Energy Laboratory, University of Wisconsin; 2010 [4/11/2017]. Available from: http://sel.me.wisc.edu/trnsys.

  74. Sousa J, editor Energy simulation software for buildings: review and comparison. International Workshop on Information Technology for Energy Applicatons-IT4Energy; 2012; Lisabon: Citeseer.

  75. Fanger PO. Thermal comfort: analysis and applications in environmental engineering. Copenhagen: Danish Technical Press; 1970.

    Google Scholar 

  76. Fanger PO. Calculation of thermal comfort: introduction of a basic comfort equation. ASHRAE Trans. 1967;73(2):4.

    Google Scholar 

  77. Gagge AP, Stolwijk JAJ, Hardy JD. Comfort and thermal sensations and associated physiological responses at various ambient temperatures. Environ Res. 1967;1(1):1–20.

    CAS  PubMed  Google Scholar 

  78. Fanger PO. Introduction of the olf and the decipol units to quantify air pollution perceived by humans indoors and outdoors. Energy and Buildings. 1988;12(1):1–6.

    Google Scholar 

  79. Gunnarsen L, Fanger PO. Adaptation to indoor air pollution. Environ Int. 1992;18(1):43–54.

    CAS  Google Scholar 

  80. Grabe JV, Svoboda P, Bäumler A. Window ventilation efficiency in the case of buoyancy ventilation. Energy Buildings. 2014;72:203–11.

    Google Scholar 

  81. Grabe JV. Flow resistance for different types of windows in the case of buoyancy ventilation. Energy Buildings. 2013;65:516–22.

    Google Scholar 

  82. Kosonen R, Tan F. The effect of perceived indoor air quality on productivity loss. Energy Buildings. 2004;36(10):981–6.

    Google Scholar 

  83. Wyon DP. The effects of indoor air quality on performance and productivity. Indoor Air. 2004;14(s7):92–101.

    PubMed  Google Scholar 

  84. Wargocki P, Wyon DP, Sundell J, Clausen G, Fanger PO. The effects of outdoor air supply rate in an office on perceived air quality, sick building syndrome (SBS) symptoms and productivity. Indoor Air. 2000;10(4):222–36.

    CAS  PubMed  Google Scholar 

  85. McCartney KJ, Humphreys MA. Thermal comfort and productivity. Proceedings of Indoor Air. 2002;2002:822–7.

    Google Scholar 

  86. Huizenga C, Abbaszadeh S, Zagreus L, Arens EA. Air quality and thermal comfort in office buildings: results of a large indoor environmental quality survey. In: de Oliveira Fernandes E, Gameiro da Silva M, Rosado Pinto J, eds. Proceedings of Healthy Buildings Lisbon 2006; p. 393–7.

  87. Janssen CP, Gray WD. When, what, and how much to reward in reinforcement learning-based models of cognition. Cogn Sci. 2012;36(2):333–58.

    PubMed  Google Scholar 

  88. Schwartz SH. Normative influences on altruism. Adv Exp Soc Psychol. 1977;10:221–79.

    Google Scholar 

  89. Stern PC. New environmental theories: toward a coherent theory of environmentally significant behavior. J Soc Issues. 2000;56(3):407–24.

    Google Scholar 

  90. Vinciarelli A, Esposito A, André E, Bonin F, Chetouani M, Cohn JF, et al. Open challenges in modelling, analysis and synthesis of human behaviour in human–human and human–machine interactions. Cogn Comput. 2015;7(4):397–413.

    Google Scholar 

Download references

Funding

This research is being funded by the Forschungsförderungsfond (FFF) Liechtenstein.

Author information

Authors and Affiliations

  1. Institute for Architecture and Planning, University of Liechtenstein, Fürst-Franz-Josef-Strasse, 9490, Vaduz, Liechtenstein

    Jörn von Grabe

Authors
  1. Jörn von Grabe
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jörn von Grabe.

Ethics declarations

Conflict of Interest

The author declares that he has no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

Graphical overview of the algorithm and the sequence of calculations. Each submodel is highlighted by different colors. The calculations start at the top and flows downwards from submodel to submodel. Within each submodel, the calculations begin from the far right and move on to the blended value (or its modification) determined in the submodel.

figure a

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

von Grabe, J. Using the Instance-Based Learning Paradigm to Model Energy-Relevant Occupant Behaviors in Buildings. Cogn Comput 12, 71–99 (2020). https://doi.org/10.1007/s12559-019-09672-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-019-09672-w

Keywords

Search

Navigation