Self-Organizing Agents for an Adaptive Control of Heat Engines

International audience Controlling heat engines imposes to deal with high dynamics, non-linearity and multiple interdependencies. A way handle these difficulties is enable the controller to learn how the engine behaves, hence avoiding the costly use of an explicit model of the process. Adaptive Mult...

Full description

Bibliographic Details
Published in:Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics
Main Authors: Boes, Jérémy, Migeon, Frédéric, Gatto, François
Other Authors: Systèmes Multi-Agents Coopératifs (IRIT-SMAC), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)
Format: Conference Object
Language:English
Published: HAL CCSD 2013
Subjects:
Multi-agent systems
Self-organization
Intelligent control systems
[INFO.INFO-MA]Computer Science [cs]/Multiagent Systems [cs.MA]
Iceland
Online Access:https://hal.science/hal-04083843
https://hal.science/hal-04083843/document
https://hal.science/hal-04083843/file/boes_12476.pdf
https://doi.org/10.5220/0004483302430250
Description
Summary:International audience Controlling heat engines imposes to deal with high dynamics, non-linearity and multiple interdependencies. A way handle these difficulties is enable the controller to learn how the engine behaves, hence avoiding the costly use of an explicit model of the process. Adaptive Multi-Agent Systems (AMAS) are able to learn and to adapt themselves to their environment thanks to the cooperative self-organization of their agents. A change in the organization of the agents results in a change of the emergent function. Thus we assume that AMAS are a good alternative for complex systems control, reuniting learning, adaptivity, robustness and genericity. In this paper, we present an AMAS for the control of heat engines and show several results.

Similar Items