Information Technology Reference
In-Depth Information
Controlling the Heating System of an Intelligent Home
with an Artificial Immune System
Martin Lehmann and Werner Dilger
Chemnitz University of Technology
09107 Chemnitz, Germany
martin.lehmann@s2000.tu-chemnitz.de,
dilger@informatik.tu-chemnitz.de
Abstract.
Intelligent Home is nowadays an established technology. Actually,
most existing realizations of the Intelligent Home cannot really adapt to the
needs of the inhabitants of the home so that they can learn typical user behavior.
In this paper we present an AIS that can perform the usual control functions but
in addition is also able to adapt to varying requirements and to learn. The AIS is
network based. The antigens represent the requests to the home and the
antibodies the responses to these requests. Both incorporate the relevant
parameters in their structure. Antibodies are produced according to the bone
marrow model and a sort of reinforcement learning mechanism is implemented.
The operation of the AIS is described by a scenario.
Keywords:
Intelligent home, AIS-network, B-cell, antibody, antigen, adaptation.
1 Introduction
The intelligent home (iHome) is a technology that is in use since about the nineties as
a by-product of building automation. It comprises several functions of which usually
not all are installed in a realization. The mostly used functions are those for the
security of the home. Other useful functions are control of temperature (heating and
cooling) and of light. Existing realizations of the iHome operate with standard
routines controlling certain parameters that are preset by the user. They cannot adapt
themselves to varying requests of the users and they cannot learn typical user
behavior and predict the needs of the users, in other words, they are not intelligent in
the meaning of the word as it is used in AI or CI.
A first step to the control of an iHome by means of an AIS was made in [2].
However, only some terminology from AIS was adopted in that paper, it lacked a
deep understanding of AIS principles. Mozer has done a lot of interesting work in
building an iHome (his own one) (cf. [8]). His approach is based on neural networks,
probably because he is a psychologist working in the Cognitive Neuroscience
community at Boulder.
The iHome can be viewed as a kind of robot, though not a mobile but a stationary
one. It is equipped with sensors and effectors of different types according to the needs
of its functions. However, there are some important differences between the iHome
and normal robot. The robot can be viewed more or less as a point-like entity,
