A router-based management system for prediction of network congestion

Network Management System (NMS) plays an important role in networks to maintain the best performance of a network. It employs variety of tools, applications, and devices in order to support network administrators to monitor and maintain the stability of a network. Fault management is part where the NMS dealing with problems and failures, such as congestion, in the network. Generally, most NMSs use Simple Network Management Protocol (SNMP) to monitor and map network availability, performance, and error rates. In the existing NMS process, an SNMP agent is deployed to get information about the network condition and then send them to the administrator for taking further action on solving the problems. However, deploying such agent to the network may increase the traffic density. On the other hand, packet latency and RTT will increase as well. In this paper, we implemented a prototype of the proposing novel system that no need to deploy such agent to obtain network information. Our system analyze the streaming traffic by implementing a Service-oriented Router (SoR). Our objective is to predict a congestion in the specific link in the network through a router-based data traffic analysis using a Bayesian network model. The purpose of the prediction is to support the network administrator to notify the early warning regarding to the fault in the network as long as possible before it actually happening. By this prediction, the network administrator can immediately taking action to avoid the problems.We provided simulation experiment to demonstrate the performance of the proposed system. Our simulation results show that the proposed system can predict a congestion link caused by a particular problem, before hand it is getting congested.