Abstract
Ubiquitous and pervasive computing deals with the design of autonomous and adaptive systems and services that interact with the closest environment enhanced by context awareness and emergence functionalities. In this article, we investigate the relationships between the environment, the actions (services), and the selection algorithm that is guaranteed to take the system to a state that suits a stochastically changing environment. Making the assumption that peering relationships between potential actions can be specified by an affinity network, the action selection mechanism is translated into an iterative algorithm that lets each activity update its strength until it converges to a solution. In pervasive environments, where services and devices interfere with each other, the proposed action selection approach prevents unexpected and undesirable behaviors or oscillating loops in a such dynamic environment.
Supplemental Material
Available for Download
The proof is given in an electronic appendix, available online in the ACM Digital Library.
- Bakhouya, M. 2008. A reinforcement learning based approach for spontaneous service emergence in pervasive computing environments. Int. Trans. Syst. Sci. Appl. 4, 2, 181--187.Google Scholar
- Bakhouya, M. and J. Gaber. 2006. Adaptive approach for the regulation of a mobile agent population in a distributed network. In Proceedings of the International Symposium on Parallel and Distributed Computing (ISPDC’06). IEEE, 1132--1140. Google Scholar
Digital Library
- Farmer, J. D., Packard, N. H., and Perelson, A. 1986. The immune system, adaptation and machine learning. Physica 22D, 187--204. Google Scholar
Digital Library
- Gaber, J. 2007. Spontaneous emergence model for pervasive environments. In Proceedings of the Globecom Workshops.Google Scholar
Cross Ref
- Holland, J. 1995. Escaping Brittleness: The Possibilities of General-Purpose Learning Algorithms Applied to Parallel Rule-Based Systems. In Computation and Intelligence: Collected Readings, G. F. Luger Ed. American Association for Artificial Intelligence, Menlo Park, CA, 275--304. Google Scholar
Digital Library
- Horn, R. and Johnson, C. 1999. Matrix Analysis. Cambridge University Press.Google Scholar
- Jerne, N. 1974. Towards a network theory of the immune system. Ann. Immunol. (Inst. Pasteur). 125, 373--389.Google Scholar
- Russell, S. and Norvig, P. 2006. Intelligence Artificielle. Pearson Education, France.Google Scholar
- Suzuki, J. and Yamamoto, Y. 2000. Building an artificial immune network for decentralized policy negotiation in a communication endsystem: Openwebserver/inexus study. In Proceedings of the 4th World Multiconference on Systemics, Cybernetics and Informatics.Google Scholar
- Watanabe, Y., Ishiguro, A., and Uchikawa, Y. 1998. Decentralized behavior arbitration mechanism for autonomous mobile robot using immune system. In Artificial Immune Systems and Their Applications. Springer, 186--208.Google Scholar
- Zamudio, V. and Callaghan, V. 2006. Unwanted periodic behaviour in pervasive computing environments. In Proceedings of the ACS/IEEE International Conference on Pervasive Services (ICPS’06). IEEE, 26--29. Google Scholar
Digital Library
Index Terms
Action Selection Algorithms for Autonomous System in Pervasive Environment: A Computational Approach
Recommendations
Pervasive 2004: A Viennese Treat
At the 2nd International Conference on Pervasive Computing, researchers and practitioners in all areas of pervasive and ubiquitous computing met in palatial surroundings to participate in workshops, technical presentations, and a doctoral colloquium.
System support for pervasive applications
Pervasive computing provides an attractive vision for the future of computing. Computational power will be available everywhere. Mobile and stationary devices will dynamically connect and coordinate to seamlessly help people in accomplishing their ...
Toward autonomic pervasive computing
iiWAS '08: Proceedings of the 10th International Conference on Information Integration and Web-based Applications & ServicesThe Autonomic Pervasive Computing can simplify the complexity of the configuration, maintenance and management of pervasive environments such as smart spaces. The Pervasive Computing is a paradigm where the information processes are distributed in the ...






Comments