AGENT TECHNOLOGY
FOR VIRTUAL ORGANIZATIONS
Vladimir Marik
Department of Cybernetics. Czech Technical University in Prague. Czech Republic &
Rockwell Automation Research Center. Americka 22. 12000 Prague. CZECH REPUBLIC.
marik@labe.felk.cvut.cz
Michal Pechoucek
Department of Cybernetics. Czech Technical University in Prague. CZECH REPUBLIC
pechouc@labe.felk.cvut.cz
The paper summarizes the latest achievements in the area of intelligent
agent-based solutions for manufacturing. The main idea of this paper is
that many solutions developed in the multi-agent area can be
successfully rellsed for the virtual enterprise purposes. Critical analysis
of both the MAS advantages and gaps frol/l the VO point of view is
presented.
1. INTRODUCTION
Both the complexity of the environment where we live and operate as well as the
complexity of tasks to be solved is growing rapidly. In many situations, the
centralized and hierarchically organized decision-making and solutions are not
adequate and fail just because of complexity of tasks to be solved and requirements
to be put on these tasks.
To overcome the complexity barrier, it is quite natural to consider sets of
autonomous, efficiently cooperating units being easily integrated by the "plug-and-
play" approach instead of the rigid, centralized architectures. This is a clearly visible
trend on all the levels of manufacturing and businesses. On the real-time level where
these units are tightly physically linked to the manufacturing hardware we talk about
holons and holonic solutions; intelligent agents are helping to solve the production
planning and scheduling tasks on the workshop and plant levels. The vision of
internet-based cooperation among enterprises has lead to the idea of virtual
enterprises: "A virtual enterprise is a temporary alliance of enterprises that come
together to share skills or core competencies and resources in order to better respond
to business opportunities, and whose cooperation is supported by computer
networks." (Camarinha-Matos & Afsarmanesh, 1999).
The philosophical background of all these approaches is the same: efficient
coordination and cooperation among autonomous intelligent goal-oriented units can
lead to a quite effective behavior of the community as a whole. Knowledge stored
and applied locally provides interesting and useful patterns of emergent behavior.
L. M. Camarinha-Matos et al. (eds.), Processes and Foundations for Virtual Organizations
© IFIP International Federation for Information Processing 2004