Enabling proactive self-healing by data mining network failure logs

Hashmi, Umair Sajid; Darbandi, Arsalan; Imran, Ali

doi:10.1109/iccnc.2017.7876181

Cited by 37 publications

(18 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For more information on K-means, please refer to [26]. In SON, K-means can be found in mobility optimization [60], caching problems [82], resource optimization [56], [88], fault detection [108], and cell outage management [103].…”

Section: B Unsupervised Learningmentioning

confidence: 99%

“…In cellular networks, SOM can be applied in the configuration of operational parameters [83], coverage and capacity optimization [110], HO management [89], [90], resource optimization [83], fault detection [93]- [96], [108], [111], and cell outage management [52].…”

Section: B Unsupervised Learningmentioning

confidence: 99%

“…In cellular systems, anomaly detection algorithms are used mainly in self-healing to detect abnormal network behavior [97]- [102], [108], fault classification [98], [99], and perform cell outage management [9], [49], [50], [52], [70], [71], [104], [105], [107], [115], [116].…”

Section: B Unsupervised Learningmentioning

confidence: 99%

“…In [108]. Hashmi et al, compare five different unsupervised learning algorithms (K-means, Fuzzy C-means, SOM, local outlier factor, and local outlier probabilities) in order to detect faults in the network.…”

Section: A Fault Detectionmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: B Unsupervised Learningmentioning

confidence: 99%

Section: B Unsupervised Learningmentioning

confidence: 99%

Section: B Unsupervised Learningmentioning

confidence: 99%

Section: A Fault Detectionmentioning

confidence: 99%

See 2 more Smart Citations

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

show abstract

“…Em [3] é desenvolvida uma plataforma de detecção de anomalias e análise de causa raiz (RCA), baseada na mineração de regras de associação combinadas com abordagens estatísticas para identificar as anomalias. Em [4], por exemplo, são comparados cinco algoritmos de aprendizado não supervisionado (K-means, Fuzzy C-means, Local Outlier Factor, Local Outlier Probabilities e Kohonen's Self Organizing Maps (SOM)) com o intuito de detectar falhas na rede. Os resultados mostraram que o SOM apresentou desempenho superior ao K-means e Fuzzy C-means.…”

Section: Introductionunclassified

Proposta de um método de análise do desempenho de redes móveis com base na representação dimensional de KPIs usando PCA e clusterização

Correa¹,

Pinheiro²,

Nunes³

2019

Anais De XXXVII Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

Resumo-A complexidade, abrangência e quantidade de dados produzida pelas redes móveis têm exigido novos métodos para uma análise mais automatizada e capaz de buscar por padrões de anomalias não-óbvios. Neste sentido, esta pesquisa sugere um método de detecção de anomalias baseado em redução de dimensionalidade, clusterização de indicadores de desempenho e segmentação em diferentes períodos do dia. O método foi avaliado usando seis indicadores de uma rede em operação e os resultados encontrados encorajam o uso do método como ferramenta para nortear a correção de falhas, otimizar recursos e indicação de expansão de capacidade da rede. Palavras-Chave-Detecção de anomalias, redução de dimensionalidade, clusterização, indicadores de desempenho, rede celular.

show abstract

5G Development: Automation and the Role of Artificial Intelligence

2020

View full text Add to dashboard Cite

5G is expected to be commercially rolled out by 2020 and targets challenging KPI requirements. Due to the increased complexity of the mobile networks, meeting the requirements by the existing manual network operation techniques is infeasible for 5G. Also, the manual daily network operations escalate mobile networks Operation Expenses (OPEX). Without a dramatic increase in OPEX, dealing with the network complexity and meeting the KPIs for each challenging use case is only possible by the realization of autonomous network operation functions. The autonomous networks' components and the intelligent functions are developed with the cutting edge Machine Learning (ML) and Artificial Intelligence (AI) models. Furthermore, to be able to realize the efficient and scalable network automation capabilities, ONAP (Open Network Automation Platform) and OSM (Open Source Management and orchestration) frameworks are proposed for 5G. These frameworks provide a set of plug and play automation functions as well as APIs, which enables the mobile operators to extend the framework capabilities by developing their network automation functions to tackle their individual business and operational challenges. The automated network management and orchestration function, in turn, enables the operators to keep the OPEX to reasonable levels and meet the challenging KPI requirements of 5G. This article as a baseline provides an overview of 4G Long‐Term Evolution (LTE) Self‐Organizing Networks (SON) and presents 5G automation concepts and frameworks. Furthermore, in this article, the prominent 5G automation frameworks namely ONAP and OSM are compared, and evidently, the ONAP framework has enriched network automation functions and stands out as the choice of the majority of the telecommunication industry. Finally, this article summarizes the cutting edges AI models and provides a literature review on AI applications in the scope of mobile network automation.

show abstract

Enabling proactive self-healing by data mining network failure logs

Cited by 37 publications

References 13 publications

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

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

Proposta de um método de análise do desempenho de redes móveis com base na representação dimensional de KPIs usando PCA e clusterização

5G Development: Automation and the Role of Artificial Intelligence

Contact Info

Product

Resources

About