Efficacy of Fuzzy Representation of Knowledge for Integrated Management of Networked Systems

For most modern networked systems, the traditional element-based management views are replaced by integrated management structures that take the nature of the enterprises and the services they provide into account. These complex systems need capabilities to accommodate for diverse areas, ranging from administration of elements to provision of services and management of the enterprise itself. This is not an easy task. While many automated approaches are in use, to a large extent the effectiveness of the integrated management depends on understanding the functions of its components and their relations with one another. For most organizations, it is impossible to ascertain models that describe various roles, functions, and interactions of such components in a precise and yet useful manner. As such, human interactions are crucial for their proper operations. Human intelligence is for instance needed to deal with the incoherent and conflicting data with varying degrees of relevance for managing the tasks in hand. Such a need is also a direct consequence of the extensive utilization of linguistic variables in communication amongst staff and managers. In this work, these points are further discussed leading to elaboration of ways to utilize fuzzy modeling to improve integrated management effectiveness. We propose an integrated management design framework, which is based on multiple agents, where each human role is supported by an agent. It will be shown that through facilitating the cooperation among the entities involved in a given task, the framework can result in improving the effectiveness of the integrated management.