Introducing Automated Reasoning in Network Management

Abstract

This paper proposes the adoption of Artificial Intelligence techniques in the field of network management and monitoring. In order to allow automated reasoning on networking topics, we constructed an accurate ontological model capable of fitting as more as possible networking concepts. The thoroughly representation of the domain knowledge is used by a Logical Reasoner, which is an expert system capable of performing management tasks typically executed by human experts. The Logical Reasoner is integrated in a distributed multi-agent architecture for network management, which exploits the dynamic reasoning capabilities of the Situation Calculus formalism to provide a powerful system capable of performing high-level management tasks in order to deal with network fault situations. The system exploits programmable network technology to make possible the deployment of code which implements teleo-reactive agents, distributed across the whole network. The information related to network events, generated by programmable sensors deployed on the network devices, is collected by the logical entity where it is merged with general domain knowledge, with a view to identifying the root causes of faults, and to decide on reparative actions.