Controlling the Heating System of an Intelligent Home with an Artificial Immune System - Artificial Immune Systems - page 348

rooms. In all these cases, the system adapted pretty well to the various requirements.
In addition, we did some tests to determine optimal values for the relevant parameters
in the system like mutation rate and adaptation of concentration.
Further developments on an AIS for the intelligent home should include other
components of the home, e.g. the lighting system. We have already developed an AIS
for such a system, but this is based on the clonal selection theory, and it turned out
that the results are not as convincing as those based on a network approach. The
appropriate choice of the parameter values is always a problem in an AIS. It depends
on the deployment of the AIS therefore it would be a good idea to have some kind of
meta-learning system that is able to adapt the parameters to the current application.
Finally, the question remains about the actual deployment in a house that has all
the required technology at its disposal. The heating control system we have presented
has a clearly defined interface to the outside world, in this case to the world of the
hardware of the heating system via the central unit. It is responsible for the translation
of incoming signals into antigens and it produces commands to the heating system
from the antibodies. For the test of the system it does not matter if the signals are real
or simulated. However in general, reality is different from simulation to some degree.
Therefore we hope that we can connect it one day to the iPhon-software of ESF
Software Company. iPhon is a control system for building automation ([6]) but has
also been deployed for the control of iHomes. If the AIS will be successfully tested in
combination with iPhon, it may be possible to implement it in one of the homes where
iPhon is in use.
References
1. L.N. de Castro and F.J. von Zuben. aiNET: An artificial immune network for data analysis.
In Data Mining: A heuristic approach, H.A. Abbass, R.A. Sarker, and C.S. Newton (eds.),
Idea Group Publishing, USA, 2001, 231 - 259
2. W. Dilger. Decentralized autonomous organization of the intelligent home according to the
principle of the immune system. In Proceedings of IEEE System, Man, and Cybernetics
Conference, Orlando 1997, 351 - 356.
3. J.D. Farmer, S.A. Kauffman, N.H. Packard, and A.S. Perelson. Adaptive dynamic networks
as models for the immune system and autocatalytic sets. Ann. of the New York Academy of
Sciences , 504, 1987, 118 - 131
4. E. Hart, P. Ross, A. Webb, and A. Lawson. A role for immunology in “Next generation”
robot controllers. In Proceedings of ICARIS 2004 , Edinburgh, Springer LNCS 2787, 2003,
46 - 56
5. A. Ishiguro, Y. Watanabe, T. Kondo, Y. Shirai, and Y. Uchikawa. Immunoid. A robot with a
decentralized behavior arbitration mechanisms based on the immune system. In Proceedings
of ICMAS Workshop on Immunity-Based Systems . Nagao, 1996, 82 - 92
6. ESF Software GmbH. http://www.esf-software.com/de/home/index.php
7. M. Krautmacher, W. Dilger. AIS based robot navigation in a rescue scenario. In
Proceedings of ICARIS 2005 , Catania, 2005, Springer LNCS 3239, 106 - 118
8. M.C. Mozer. Lessons from an adaptive house. In D. Cook and R. Das (eds.), Smart
environments: Technologies, protocols, and applications . Hoboken, NJ, J. Wiley & Sons,
2005, 273 - 294