ABSTRACT
The concept of distributed artificial intelligence (DAI) originates from the real world where many cases are inherently distributed in space, function, knowledge, expertise or information (Durfee et al., 1989). The notion of DAI provides a natural metaphor to match such distribution. It represents a new way of analysing, designing and implementing complex software systems. The key advantage of DAI is its responsibility for enacting various components of the business process, which is delegated to a number of autonomous agents. These agents act collectively as a society and collaborate to achieve their own individual goals as well as the common goal of the society to which they belong (Ugwu et al., 1999a). Agents are inherently modular and can be constructed locally for each resource, provided they satisfy some high-level protocol of interaction.
