Monitoring of a Large Wi-Fi Hotspots Network: Performance Investigation of Soft Computing Techniques

This paper addresses the problem of network monitoring by investigating the performance of three soft computing techniques, the Artificial Neural Network, Bayesian Network and the Artificial Immune System. The techniques were used for achieving 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 algorithms into a data collection system to detect anomalous performance and aberrant behavior in the ISP’s network. The results are therefore revealed and discussed in terms of both anomaly performance and aberrant behavior on several test case scenarios