Abstract
The usual approach to ambient intelligence is an expert modeling of the devices present in the environment, describing what each does and what effect it will have. When seen as a dynamic and noisy complex systems, with the efficiency of devices changing and new devices appearing, this seems unrealistic. We propose a generic multi-agent (MAS) learning approach that can be deployed in any ambient environment and collectively self-models it. We illustrate the concept on the estimation of power consumption. The agents representing the devices adjust their estimations iteratively and in real time so as to result in a continuous collective problem solving. This approach will be extended to estimate the impact of each device on each comfort (noise, light, smell, heat...), making it possible for them to adjust their behaviour to satisfy the users in an integrative and systemic vision of an intelligent house we call QuaLAS: eco-friendly Quality of Life in Ambient Sociotechnical systems.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Cities, grids, homes, environments...
- 2.
- 3.
Scenarios for ambient intelligence in 2010 (ISTAG 2001 Final Report) (2001) by K. Ducatel, M. Bogdanowicz, F. Scapolo, J. Leijten, J. C. Burgelma.
- 4.
Adding devices, changing or removing some.
- 5.
Due to imprecise or low-quality sensors.
- 6.
Even partial or imprecise, possibly linked with a certainty coefficient or trust.
- 7.
The solver has to start learning in real time and not wait for a specific data set.
- 8.
Result or behaviour of the system considered satisfactory by an external observer.
- 9.
Self-stabilizing, self-organizing, self-observation, self-optimizing, self-managing...
- 10.
Or life cycle of the agents: perceive, decide, act.
- 11.
It is uncertain as some agents may be part of other more critical situations.
References
Amouroux, É., Huraux, T., Sempé, F., Sabouret, N., Haradji, Y.: SMACH: agent-based simulation investigation on human activities and household electrical consumption. In: Filipe, J., Fred, A. (eds.) ICAART 2013. CCIS, vol. 449, pp. 194–210. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44440-5_12
Bonte, M., Thellier, F., Lartigue, B.: Impact of occupant’s actions on energy building performance and thermal sensation. Energy Build. 76, 219–227 (2014)
Georgé, J.P., Gleizes, M.P., Camps, V.: Cooperation. In: Di Marzo Serugendo, G., Gleizes, M.P., Karageorgos, A. (eds.) Self-organising Software. Natural Computing Series, pp. 193–226. Springer, Heidelberg (2011)
Guivarch, V., Camps, V., Péninou, A., Glize, P.: Self-adaptation of a learnt behaviour by detecting and by managing user’s implicit contradictions. In: IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT 2014), Warsaw, Poland, pp. 24–31. IEEE Computer Society (2014)
Huraux, T.: Multi-agent simulation of a complex system: combining domains of expertise with a multi-level approach - the case of residential electrical consumption. Ph.D., UPMC - Paris 6 Sorbonne Universités, October 2015
Sarda, P.: La maison de l’an 2000. INA - reportage TF4, October 1979. https://www.ina.fr/video/CAA7901376201
Weiser, M.: The computer for the 21st century. Sci. Am. 265(3), 66–75 (1991). http://www.ubiq.com/hypertext/weiser/SciAmDraft3.html
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Crasnier, F., Georgé, JP., Gleizes, MP. (2019). Real-Time Learning of Power Consumption in Dynamic and Noisy Ambient Environments. In: Nguyen, N., Chbeir, R., Exposito, E., Aniorté, P., Trawiński, B. (eds) Computational Collective Intelligence. ICCCI 2019. Lecture Notes in Computer Science(), vol 11684. Springer, Cham. https://doi.org/10.1007/978-3-030-28374-2_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-28374-2_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28373-5
Online ISBN: 978-3-030-28374-2
eBook Packages: Computer ScienceComputer Science (R0)