The agent routering process of a dynamic distributed decision support system

Abstract

When certain enterprise domain needs to make an unusual decision, it will probably require new kind of information. If the interaction model among domains cannot be defined because the decision scenarios are unpredictable, the system itself must search the required information analyzing where it is available, or can be generated. To do that, it is necessary to design a mechanism able to decide where to look for the information.We have developed a distributed DSS able to work in a dynamic way. This system is based on the use of mobile agents, which receive the user's queries and visit the DSS domains gathering the required information. One of the main elements to the efficient operation of this system is the Router Agent. Its responsibility is to give an adequate route to the mobile agents. In this paper we propose a structure for the Router Agent. It includes a Knowledge Base where the information managed by each domain is represented, and a mechanism to compare the query content with the domain representation. We also present an interactive strategy to obtain the initial data to be stored in the Router Knowledge Base. The AHP method is used to support the task of evaluating the relative importance among terms representing each domain.