Kohonen self-organizing maps and expert system for network virtual memory performance prediction

Authors:
Nazar Elfadil;Mohamed Khalil Hani;Sulaiman Mohd Nor;Sheikh Hussein
Affiliations:
MiCE Department, Faculty of Electrical Engineering, University of Technology Malaysia, 81310 UTM Skudai, Johor, Malaysia;MiCE Department, Faculty of Electrical Engineering, University of Technology Malaysia, 81310 UTM Skudai, Johor, Malaysia;MiCE Department, Faculty of Electrical Engineering, University of Technology Malaysia, 81310 UTM Skudai, Johor, Malaysia;MiCE Department, Faculty of Electrical Engineering, University of Technology Malaysia, 81310 UTM Skudai, Johor, Malaysia
Venue:
Systems Analysis Modelling Simulation - Special issue: Advances in control and computer engineering
Year:
2002

Citing 3
Cited 0

Automated knowledge acquisition

Automated knowledge acquisition
Self-organizing maps

Self-organizing maps
Neural Networks Approach to Rule Extraction

ANNES '95 Proceedings of the 2nd New Zealand Two-Stream International Conference on Artificial Neural Networks and Expert Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

A basic reason why we monitor the performance of a system is to define the overall state of the machine ("It's Ok or "It's slow" etc). In other words to determine whether the system is experienceing a bottleneck or not. This paper investigates the application of Self Organizing Maps (SOM) and Expert System (ES) in the network performance management area. A system is proposed which collects data from certain server and processes the data in order to get knowledge concerning the current network performance or predicts the network performance. To demonstrate the applicability of the proposed method to network performance domain problems, a case study in virtual memory performance status (vmstat) domain is presented.