Detecting anomalies in cellular networks using an ensemble method

Ciocarlie, Gabriela F.; Lindqvist, Ulf; Nováczki, Szabolcs; Sanneck, Henning

doi:10.1109/cnsm.2013.6727831

Cited by 56 publications

(31 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To cope with all types of KPIs, we propose to extend the topic-modeling framework ( Figure 2) to include output from our previous work on cell-level anomaly detection [3], [4]. Hence, for the neutral KPIs we propose to use the KPI degradation level generated by our ensemble method when applied …”

Section: A Topic Modeling Using Neutral Kpismentioning

confidence: 99%

See 1 more Smart Citation

Managing scope changes for cellular network-level anomaly detection

Ciocarlie

Cheng

Connolly

et al. 2014

2014 11th International Symposium on Wireless Communications Systems (ISWCS)

Self Cite

View full text Add to dashboard Cite

The Self-Organizing Networks (SON) concept is increasingly being used as an approach for managing complex, dynamic mobile radio networks. In this paper we focus on the verification component of SON, which is the ability to automatically detect problems such as performance degradation or network instability stemming from configuration management changes. In previous work, we have shown how Key Performance Indicators (KPIs) that are continuously collected from network cells can be used in an anomaly detection framework to characterize the state of the network. In this study, we introduce new methods designed to handle scope changes. Such changes can include the addition of new KPIs or cells in the network, or even re-scoping the analysis from the level of a cell or group of cells to the network level. Our results, generated using real cellular network data, suggest that the proposed network-level anomaly detection can adapt to such changes in scope and accurately identify different network states based on all types of available KPIs.

show abstract

Section: A Topic Modeling Using Neutral Kpismentioning

confidence: 99%

“…Illustration of topic modeling on clustering both non-neutral and neutral KPI data in a multi-level clustering framework. For the nonneutral KPIs, the raw KPI values are used, while for the neutral KPIs, the KPI degradation level computed by our cell-level anomaly detection framework [3], [4].…”

Section: Features (Neutral Kpis)mentioning

confidence: 99%

Managing scope changes for cellular network-level anomaly detection

Ciocarlie

Cheng

Connolly

et al. 2014

2014 11th International Symposium on Wireless Communications Systems (ISWCS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the cellular networks domain, SVM is being applied in self-optimization and self-healing scenarios, more specifically in mobility optimization [30], [68], fault detection [69] and cell outage management [70], [71].…”

Section: A Supervised Learningmentioning

confidence: 99%

“…Coluccia et al, in [45], propose a solution based on Bayes' estimators in order to estimate the values of certain KPI and forecast when a failure might occur in a 3G network scenario. On the other hand, in [69], the authors build an adaptive ensemble method to model and determine the performance status of cells in the network. The framework uses certain KPI to determine the state of a cell and uses a combination of different SVM classifiers in order to classify new observed data points.…”

Section: A Fault Detectionmentioning

confidence: 99%

A Survey of Machine Learning Techniques Applied to Self-Organizing Cellular Networks

Klaine

Imran

Onireti

et al. 2017

IEEE Commun. Surv. Tutorials

417

200

View full text Add to dashboard Cite

Abstract-In this paper, a survey of the literature of the past fifteen years involving Machine Learning (ML) algorithms applied to self organizing cellular networks is performed. In order for future networks to overcome the current limitations and address the issues of current cellular systems, it is clear that more intelligence needs to be deployed, so that a fully autonomous and flexible network can be enabled. This paper focuses on the learning perspective of Self Organizing Networks (SON) solutions and provides, not only an overview of the most common ML techniques encountered in cellular networks, but also manages to classify each paper in terms of its learning solution, while also giving some examples. The authors also classify each paper in terms of its self-organizing use-case and discuss how each proposed solution performed. In addition, a comparison between the most commonly found ML algorithms in terms of certain SON metrics is performed and general guidelines on when to choose each ML algorithm for each SON function are proposed. Lastly, this work also provides future research directions and new paradigms that the use of more robust and intelligent algorithms, together with data gathered by operators, can bring to the cellular networks domain and fully enable the concept of SON in the near future.

show abstract

“…Good examples of recent practical approaches to SH in real operational networks are found in [10,11,12,13,14,15]. For example, [10] addressed the problem of verifying the effect of network configuration changes by monitoring the state of the network and determining if the changes resulted in degradations.…”

Section: Developments In Sh Researchmentioning

confidence: 99%

Towards proactive context-aware self-healing for 5G networks

et al. 2017

View full text Add to dashboard Cite

In this paper, we suggest a new research direction and a future vision for Self-Healing (SH) in Self-Organizing Networks (SONs). The problem we wish to solve is that traditional SH solutions may not be sufficient for the future needs of cellular network management because of their reactive nature, i.e., they start recovering after detecting already occurred faults instead of preparing for possible future faults in a pre-emptive manner. The detection delays are especially problematic with regard to the zero latency requirements of 5G networks. To address this problem, existing SONs need to be upgraded from reactive to proactive response. One of the dimensions in SH research is to employ more holistic context information that includes, e.g., user location and mobility information, in addition to traditional context information mostly gathered from sources inside the network. Such extra information has already been found useful in SH. In this paper, we suggest how user context information can not only be incorporated in SH but also how future context could be predicted based on currently available information. We present a user mobility case study as an example to illustrate our idea.

show abstract

Detecting anomalies in cellular networks using an ensemble method

Cited by 56 publications

References 8 publications

Managing scope changes for cellular network-level anomaly detection

Managing scope changes for cellular network-level anomaly detection

A Survey of Machine Learning Techniques Applied to Self-Organizing Cellular Networks

Towards proactive context-aware self-healing for 5G networks

Contact Info

Product

Resources

About