ANOMALY DETECTION IN SELF-ORGANIZING NETWORKS CONVENTIONAL VERSUS.CONTEMPORARY MACHINE LEARNING
Abstract : This paper presents a comparison of conventional and modern machine (deep) learning within the framework of anomaly detection in self-organizing networks. While deep learning has gained significant traction, especially in application scenarios where large volumes of data can be collected and processed, conventional methods may yet offer strong statistical alternatives, especially when using proper learning representations. For instance, support vector machines have previously demonstrated state-of-the-art potential in many binary classification applications and can be further exploited with different representations, such as one-class learning and data augmentation. We demonstrate for the first time, on a previously published and publicly available dataset, that conventional machine learning can outperform the previous state-of-the-art using deep learning by 15% on average across four different application scenarios.
? Our fndings show that proposed deep learning approaches outperform existing feed-forward neural networks, and on the average, in more than 80% of the cases the outage states of the femtocells are correctly predicted among healthy and three anomalous states.
? Tis study aims to develop a foresight for cell outage management in existing cellular systems and forthcoming next-generation networks within multi-tiered ultra-dense deployments.
? Tis study demonstrates two deep network approaches, namely LSTM and 1D CNN, for detection and identifcation of anomalous states of densely deployed femtocells to inspire outage management in existing and upcoming cellular networks.
? COD is basically a classifcation problem about detecting the non-healthy cell among healthy ones by making use of some statistics generated by UEs, base stations, and other network components.
? Crippled FAPs have serious problems and may carry very little trafc. On the other hand, catatonic FAPs are generally out of service due to catastrophic failures like serious power cuts
? FAP’s output power due to hardware or software failures such as implementation failures in channel processing, external power supply problems or even misconfguration, FAPs undergo anomalous states from the healthy state.
? In both the proposed schemes, probable outagerelated anomalies in femto access points (FAP) are detected and classifed within predetermined time sequence intervals.
? Moreover, aggregation decision methods are also incorporated into the proposed framework for boosting cell outage detection procedure on FAP level.
? A method, based on the analysis of time evolution metrics, is proposed in for detecting faulty patterns arising from degraded cells
? Besides, a classifcation tree-based method along with cell-level aggregation foridentifcation of faulty cells is proposed
? In channel quality indicator (CQI) is used within a composite hypothesis for outage detection by means of a discriminant function. Machine learning methods are also popular in outage detection of macro-cells.
? As a variant of recurrent neural networks (RNNs), LSTM modules have been used with time sequence labeling tasks on many areas so far.
? For the optimization process, gradient descent method with back-propagation in time can be used to compute the required gradients
? On the other hand, 1D CNN is also used in data having time sequence character such as text, handwriting, speech signals, and natural language processing
|