An agent-based model of a responsive network monitoring system for internet service providers

Abstract

The purpose of this project was to develop a responsive Agent based network monitoring system designed to reduce the time taken by network administrators to initiate monitoring of network nodes and making any changes and updates on the monitoring parameters. Due to development of various technologies that interconnect most of today’s organizations, may highly rely on the Internet and Intranets for their day to day activities and thus lay a huge reliance on it. A few hours of network breakdown would incur huge losses to the organization. The widely used Simple Network Management Protocol (SNMP) is today particularly limiting due to the client-server centralized and static paradigm. The approach is Ad-hoc, centralized and relies on a limited set of capabilities at network nodes. In this paradigm, the system does not auto respond to changes and modifications in the network as hard coding is required to make the necessary changes. Our approach used a Multi Agent System (MAS) that provides a solution that works by reducing the time taken to initiate and make any changes in the monitoring parameters by introducing intelligence to the system. In this project, we used Prometheus methodology in the system specification, design and implementation. The Prometheus methodology is a detailed process for specifying, designing, and implementing intelligent agent systems. Our goal in using the Prometheus methodology was to have a process with defined deliverables. The results of the study showed that the MAS system optimizes responsiveness by ensuring changes done on the database are automatically updated to the agent’s database which makes the relevant changes on the monitored parameters.