Automated Network Fault Management

Abstract

Future military communication networks will have a mixture of backbone terrestrial, satellite and wireless terrestrial networks. The speeds of these networks vary and they are very heterogeneous. As networks become faster, it is not enough to do reactive fault management. Our approach combines proactive and reactive fault management . Proactive fault management is implemented by dynamic and adaptive routing. Reactive fault management is implemented by a combination of a neural network and an expert system. The system has been developed for the X.25 protocol. Several fault scenarios were modeled and included in the study: reduced switch capacity, increased packet generation rate of a certain application, disabled switch in the X.25 cloud, disabled links. We also modeled occurrence of alarms including severity of the problem, location of the event and a threshold. To detect and identify faults we use both numerical data associated with the performance objects (attributes) in the MIB as well as SNMP traps (alarms). Simulation experiments have been performed in order to understand the convergence of the algorithms, the training of the neural networks involved and the G2/NeurOn-Line software environment and MIB design.