Detecting traffic anomaly in wireless networks, an analytics methodology

Abstract

Since anomalies in wireless networks have different behaviors, not all of them can be detected and recognized. With the capacity of detecting and describing hidden structure from unlabeled data, unsupervised algorithms are able to automatically characterize the nature of traffic behavior and detect anomalies from normal behaviors in the wireless network. In this paper, co-occurrence data is studied since it combines traffic data with generating entities. Gaussian probabilistic latent semantic analysis (GPLSA) model is leveraged to compare the Gaussian Mixture Model (GMM) with temporal network data. A novel “Donut” algorithm of anomaly detection is proposed with model log-likelihood. Experimental results validated that the proposed GPLSA model could hold better promise in the early detection with low false alarm rate and low implementation complexity.