UCT CS Research Document Archive

Preemptive Performance Monitoring of a Large Network of Wi-Fi Hotspots: An Artificial Immune System

Machaka, Pheeha and Antoine Bagula (2011) Preemptive Performance Monitoring of a Large Network of Wi-Fi Hotspots: An Artificial Immune System. In Proceedings WIRED/WIRELESS INTERNET COMMUNICATIONS 2011 6649, pages 494-504, Vilanova i la Geltrú, Spain.

Full text available as:

Abstract

This paper addresses the problem of network monitoring by proposing an Artificial Immune System (AIS) system to achieve situation recognition and monitoring in a large network of Wi-Fi hotspots as part of a highly scalable preemptive monitoring tool for wireless networks. Using a set of data extracted from a live network of Wi-Fi hotspots managed by an ISP, we integrated an AIS algorithm into a data collection system to detect anomalous performance and aberrant behavior in the ISP’s network. The results reveal the efficiency of the AIS system in terms of both anomaly performance and aberrant behavior on several test case scenarios.

EPrint Type:Conference Paper
Keywords:Performance Monitoring, Non-Self Detectors, Artificial Immune Systems, Anomaly Detection
Subjects:C Computer Systems Organization: C.2 COMPUTER-COMMUNICATION NETWORKS
ID Code:719
Deposited By:Bagula, Antoine
Deposited On:18 November 2011
Alternative Locations:http://www.springerlink.com/content/4q21g23073m54231/