Automatic Root Cause Analysis for LTE Networks Based on Unsupervised Techniques

Abstract

The increase in size and complexity of current cellular networks is complicating their operation and maintenance tasks. While the end-to-end user experience in terms of throughput and latency has been significantly improved, cellular networks have also become more prone to failures. In this context, mobile operators start to concentrate their efforts on creating Self-Healing networks, i.e. those networks capable of performing troubleshooting in an automatic way, making the network more reliable and reducing costs. In this paper, an automatic diagnosis system based on unsupervised techniques for Long-Term Evolution (LTE) networks is proposed. In particular, this system is built through an iterative process, using SelfOrganizing Maps (SOM) and the Ward's Hierarchical method, in order to guarantee the quality of the solution. Furthermore, in order to obtain a number of relevant clusters and label them properly from a technical point of view, an approach based on the analysis of the statistical behaviour of each cluster is proposed. Moreover, with the aim of increasing the accuracy of the system, a novel adjustment process is presented. It intends to refine the diagnosis solution provided by the traditional SOM according to the so-called Silhouette index and the most similar cause on the basis of the minimum X th percentile of all distances. The effectiveness of the developed diagnosis system is validated using real and simulated LTE data by analysing its performance and comparing it with reference mechanisms.

A method for identifying faulty cells using a classification tree-based UE diagnosis in LTE

“…In the field of self-healing, several research efforts have been devoted to the development of usable automatic detection and diagnosis systems [29]. On the one hand, various mathematical approaches have been applied to analyze network measurements, such as Bayesian networks [30,31], Neural Networks [5,8], Fuzzy Logic combined with Genetic Algorithms [32], linear prediction [33], correlation [34], and statistical analysis [35,36]. However, these data-driven algorithms have been exclusively evaluated with per-cell level measurements, which may not be sufficient to manage the new data services.…”

“…The work in [8] whose aim is to diagnose problems at the cell level from traditional KPIs has been further investigated in [37] by employing call traces (as opposed to traditional KPIs) and applying a rule-based system to them. That work has been extended in [38], where a method based on Neural Networks (similar to that in [8]), is applied to diagnose the users.…”

“…That work has been extended in [38], where a method based on Neural Networks (similar to that in [8]), is applied to diagnose the users. Then, from such a user diagnosis, a threshold-based method is applied to diagnose faulty cells.…”

“…As a consequence, operators are investing a large amount of money to investigate traffic modeling and classification through packet inspection in order to better understand the characteristic of today's cellular data traffic. In addition, sophisticated traffic data filtering, processing, and correlation with other network metrics are also important features to identify root causes of any detected anomaly and increase the reliability of the network [7,8].…”

“…Compared to other techniques, such as self-organizing maps [8], classification trees are an appropriate method to improve the effectiveness of diagnosis systems, especially when faults have a critical impact on network performance (i.e., various metrics are affected). Note that this kind of faults should be attended before any other.…”