The Analysis of Network Manager’s Behaviour using a Self-Organising Neural Networks

We present a novel neural network method for the analysis and interpretation of data that describes
user interaction with a training tool. The method is applied to the interaction between trainee network managers
and a simulated network management system. A simulation based approach to the task of efficiently training
network managers, through the use of a simulated network, was originally presented by Pattinson [2000]. The
motivation was to provide a tool for exposing trainee network managers to a life like situation, where both
normal network operation and ‘fault’ scenarios could be simulated in order to train the network manager. The
data logged by this system describes the detailed interaction between trainee network manager and simulated
network. The work presented here provides an analysis of this interaction data that enables an assessment of the
capabilities of the network manager as well as an understanding of how the network management tasks are being
approached. A neural network architecture [Lee, Palmer-Brown, Roadknight 2004] is adapted and implemented
in order to perform an exploratory data analysis of the interaction data. The neural network architecture employs
a novel form of continuous self-organisation to discover key features, and thus provide new insights into the
data.

Citation:
Donelan, H.; C. Pattinson; D. Palmer-Brown and S. W. Lee. (2005). “The Analysis of Network Manager’s Behaviour using a Self-Organising Neural Networks.” International Journal on Simulation: Systems, Science and Technology, 6 (9) 22-32..