802.11 wireless simulation and anomaly detection using HMM and UBM

Abstract

Despite the growing popularity of 802.11 wireless networks, users often suffer from connectivity problems and performance issues due to unstable radio conditions and dynamic user behavior, among other reasons. Anomaly detection and distinction are in the thick of major challenges that network managers encounter. The difficulty of monitoring broad and complex Wireless Local Area Networks, that often requires heavy instrumentation of the user devices, makes 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 Model (HMM) and Universal Background Model (UBM) on data that is inexpensive to obtain. We then generate a number of network anomalous scenarios in OMNeT++/INET network simulator and compare the detection outcomes with those in baseline approaches—RawData and Principal Component Analysis. The experimental results show the superiority of HMM and HMM-UBM models in detection precision and sensitivity.

SpaMHMM: Sparse Mixture of Hidden Markov Models for Graph Connected Entities

“…In order to evaluate our model in the aforementioned scenario, we have followed the procedure of [20], performing extensive network simulations in a typical Wi-Fi network setup (IEEE 802.11 WLANg 2.4 GHz in infrastructure mode) using OMNeT++ [21] and INET [22] simulators. Our network consists of 10 APs and 100 users accessing it.…”

“…Following this idea, the weight G j,k , associated with the edge connecting nodes j and k in graph G, was set to the inverse distance between APs j and k and normalized so that max j,k G j,k " 1. As in [20], sequences were preprocessed by subtracting the mean and dividing by the standard deviation and applying PCA, reducing the number of features to 3. For MHMM, we did 3-fold cross validation of the number of mixture components M and hidden states per component S. We ended up using M " 15 and S " 10.…”