Fault Detection of Computer Communication Networks Using an Expert System
Abstract
The main objective of this study was to build an expert system for assisting the network administrator in his work of management and administration of the computer communication network. Theory of operation of the proposed expert system depends on using a time series model capable of forecasting the various performance parameters as: delay, utilization and collision frequency. When the expert system finds a difference (with certain tolerance) between the predicted value and the measured value, it informs the network administrator that there exist problems in his network either in the switch or link or router. We examine two types of network by our proposed expert system, the first one is called token bus while the second one is called token ring. When we run our expert system on these two types of computer networks, actually the expert system captures the problem when there exists an excess deviation from the network performance parameters.
DOI: https://doi.org/10.3844/ajassp.2005.1407.1411
Copyright: © 2005 Ibrahiem M.M. El Emary and Adanan I. Al Rabia. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
- 3,624 Views
- 2,802 Downloads
- 3 Citations
Download
Keywords
- Knowledge base
- inference engine
- exponential weighted moving average
- user interface
- forward chaining