802.11 Wireless Access Point Usage Simulation and Anomaly Detection

Despite the growing popularity of 802.11 wireless networks in many public places, wireless users often suffer from connectivity problems due to unstable radio conditions and dynamic user behavior among other reasons. Detecting the anomalous cases and planning to prevent such problems in advance are in the thick of major challenges that network managers encounter. Complication of monitoring such complex networks, that often requires heavy instrumentation of the user devices, makes the anomaly detection analysis even harder. In this paper we exploit 802.11 access point usage data and propose an anomaly detection technique based on Hidden Markov Models and on data that is inexpensive to obtain. We subsequently validate the proposed model by generating a number of network anomalous scenarios in OMNeT++/INET network simulator and evaluate the detection method against baseline approach (Raw Data and PCA) results. The experimental outcomes show the superiority of the proposed HMM model in detection precision and sensitivity.