Proactive microwave link anomaly detection in cellular data networks

Pan, Lujia; Zhang, Jianfeng; Lee, Patrick P. C.; Kalander, Marcus; Ye, Junjian; Wang, Pinghui

doi:10.1016/j.comnet.2019.106969

Cited by 17 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem of automated failure management in communication networks has gained lot of traction lately, with ML technologies enabling and pushing towards this automation [2]. Data collected from networks as alarms are used for either supervised-ML frameworks for failure detection [3], [4] and failure-cause identification [5], [6], or unsupervised ML frameworks for anomaly detection and identification [7], [8] when labelled data is scarce. Furthermore Ref.…”

Section: Related Workmentioning

confidence: 99%

Machine-Learning-Assisted Failure Prediction in Microwave Networks based on Equipment Alarms

Lateano

Ayoub

Musumeci

et al. 2023

2023 19th International Conference on the Design of Reliable Communication Networks (DRCN)

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Machine-Learning-Assisted Failure Prediction in Microwave Networks based on Equipment Alarms

Lateano

Ayoub

Musumeci

et al. 2023

2023 19th International Conference on the Design of Reliable Communication Networks (DRCN)

View full text Add to dashboard Cite

“…Lastly, for a heterogeneous network NFP model to be implemented, a database large enough to cover most cases of faults and failures would be needed, and as such, should span multiple different networks. However, although there are databases for Fault Detection [74]- [76], and this website has been proposed for the sharing of databases for cognitive network management in [77], to the best of our knowledge there are no databases available freely to researchers for Fault Prediction [23]. A freely available benchmark dataset of a heterogeneous network where all these methods could be used would be a first step towards bringing all these methods together.…”

Section: Perspectivesmentioning

confidence: 99%

Fault Prediction for Heterogeneous Networks using Machine Learning : a Survey

Murphy¹,

Lepers²,

Lavignotte³

2022

Preprint

View full text Add to dashboard Cite

<div>This manuscript provides a survey of Network Fault Prediction using Machine Learning from the years 1997 to 2021. Operational elements from the industry are shared to provide context. An overview of the different ML techniques that have been applied to Network Fault Prediction (NFP) is given. This is followed by a systematic review of the studies on NFP. Future research perspectives in the field are proposed.</div>

show abstract

“…Moreover, Refs. [9] and [10] focus on detecting link anomalies, while Ref. [3] investigates failure detection in cellular data networks.…”

Section: Related Workmentioning

confidence: 99%

Federated-Learning-Assisted Failure-Cause Identification in Microwave Networks

Tandel

Ayoub

Musumecil

et al. 2022

2022 12th International Workshop on Resilient Networks Design and Modeling (RNDM)

View full text Add to dashboard Cite

Machine Learning (ML) adoption for automated failure management is becoming pervasive in today's communication networks. However, ML-based failure management typically requires that monitoring data is exchanged between network devices, where data is collected, and centralized locations, e.g., servers in data centers, where data is processed. ML algorithms in this centralized location are then trained to learn mappings between collected data and desired outputs, e.g., whether a failure exists, its cause, location, etc. This paradigm poses several challenges to network operators in terms of privacy as well as in terms of computational and communication resource usage, as a massive amount of sensible failure data is transmitted over the network. To overcome such limitations, Federated Learning (FL) can be adopted, which consists of training multiple distributed ML models at multiple decentralized locations (called "clients") using a limited amount of locally-collected data, and of sharing these trained models to a centralized location (called "server"), where these models are aggregated and shared again with clients. FL reduces data exchange between clients and a server and improves algorithms' performance thanks to sharing knowledge among different domains (i.e., clients), leveraging different sources of local information in a collaborative environment. In this paper, we focus on applying FL to perform failure-cause identification in microwave networks. The problem is modeled as a multi-class ML classification problem with six pre-defined failure causes. Specifically, using real failure data from an operational microwave network composed of more than 10000 microwave links, we emulate a multi-operator scenario in which one operator has partial knowledge of failure causes during the training phase. Thanks to knowledge sharing, numerical results show that FL achieves up to 72% precision in identifying an unknown particular class concerning traditional ML (non-FL) approaches where training is performed without knowledge sharing.

show abstract

Proactive microwave link anomaly detection in cellular data networks

Cited by 17 publications

References 11 publications

Machine-Learning-Assisted Failure Prediction in Microwave Networks based on Equipment Alarms

Machine-Learning-Assisted Failure Prediction in Microwave Networks based on Equipment Alarms

Fault Prediction for Heterogeneous Networks using Machine Learning : a Survey

Federated-Learning-Assisted Failure-Cause Identification in Microwave Networks

Contact Info

Product

Resources

About