Exploiting Domain Ontologies and Intelligent Agents: An Automated Network Management Support Paradigm

Abstract

This paper presents a domain-ontology driven multi-agent based scheme for representing the knowledge of the communication Network Management System (NMS). The scope of this work is focussed on the performance analysis and fault detection functional areas which are of prime importance as far as the management of the communication network systems is considered. The proposed network knowledge model has been constructed in accordance with the CommonKADS methodology, to facilitate its reusability and shareability. In the proposed knowledge-intensive framework, the static domain-related concepts are articulated as the domain knowledge ontology. The empirical knowledge for managing the network is represented as the fault-state causal reasoning models, and it is explicitly encoded as the core knowledge of multi-agent middleware layer as heuristic production-type rules. This task-oriented experiential knowledge manipulates the domain content and structure during the diagnostic sessions. The inference chains during the agents’ cooperative problem solving are supported by the java-based networking routines in conjunction with the run-time log information. The proposed approach can be regarded as one of the pioneered steps towards representing the network knowledge via reusable domain ontology and intelligent agents for the automated network management support systems.