A recommender system architecture for predictive telecom network management

Zaman, Faisal; Hogan, Gabriel; Meer, Sven van der; Keeney, John; Robitzsch, Sebastian; Muntean, Gabriel‐Miro

doi:10.1109/mcom.2015.7010547

Cited by 19 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…ratings) given by users aiming to suggest relevant items to the interested users (e.g. books to read, mobile applications to download, VNFs to instantiate or even tests to validate a whole NS) [21]. RSs are moving a step forward since recommendations can be of various types of items, depending on the underlying domain (such as web sites, applications, software, VNFs, NSs or test functions).…”

Section: Recommendation Systemsmentioning

confidence: 99%

Test Recommendation for Service Validation in 5G Networks

Touloupos

Kapassa

Kyriazis

et al. 2020

Information Systems

View full text Add to dashboard Cite

System Testing is the testing of a fully integrated software, as well as a series of different tests whose purpose is to exercise the full computer-based system. Software testing though, is an arduous and expensive activity. In the context of manual testing, any effort to reduce the test execution time and to increase defect findings is welcome. One of the biggest challenges in the upcoming 5G era is the validation and verification of VNFs and NSs, so that operators can be sure of their behavior in different execution environments. 5G technologies as well as SDNs are already introducing great challenges in the field service validation, testing and optimization of the underlying network. Considering the above, we propose a recommendation system acting as a Decision Support Mechanism integrated in an SDN environment. Its purpose is the proposition of tests to the software developers towards a stable NS ready to be deployed to the production environment.

show abstract

Section: Recommendation Systemsmentioning

confidence: 99%

Test Recommendation for Service Validation in 5G Networks

Touloupos

Kapassa

Kyriazis

et al. 2020

Information Systems

View full text Add to dashboard Cite

show abstract

“…Through the introduction of the virtualized era, telecom networks generate massive amounts of monitoring data consisting of observations on network faults, configuration, accounting, performance, and security. E-stream also included a predictive, automated network management recommendation with surprising results due to the ever-increasing complexity of the networks, correlated with particular business level constraints [49]. Through the exploitation of the profound streams of data and the efficient application of techniques in dimension reduction, E-stream was based on recommending actions with four different aligned factors, namely the context, audience, existing responses, and validation.…”

Section: Nfv-catalogues and Recommendationsmentioning

confidence: 99%

Managing and Optimizing Quality of Service in 5G Environments Across the Complete SLA Lifecycle

Kapassa¹,

Touloupou²,

Stavrianos³

et al. 2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

The 5G is the fifth generation of mobile broadband, cellular technologies, and networks that promises a major change in mobility by evolving connected business realities. In such an emerging environment, reliable Service Level Agreements (SLA) and anticipation of breaches of Service Level Objectives (SLO) become compulsory. Thus, guaranteeing the required service quality, while also ensuring efficient recourse allocation becomes a challenge. In addition, 5G networks are expected to provide diverse Quality of Service (QoS) guarantees for a wide range of services, applications and users with a variety of requirements. However, there is an increased difficulty in translating user-friendly business terms into resource-specific monitoring attributes that can be used to manage resources in the 5G core network. To address these gaps, an SLA management framework, enabling QoS provisioning is introduced. The aforementioned framework will be supported by an adaptive monitoring algorithm, which removes the static time interval used in the monitoring system, in order to provide highly accurate information in real time, without the produce of unnecessary traffic to the network. The proposed architecture also incorporates a recommendation mechanism to determine the significance of various QoS parameters in order to ensure that relevant QoS metrics are included in the SLAs, using enriched metadata information from a Network Function Virtualization (NFV) Catalogue.

show abstract

“…Zaman et al address the challenge of knowledge management due to the vast amount of data and numerous data sources present in a typical CSP. They propose a solution for CSP network management that is capable of extracting knowledge from streams of data based on pattern generation and recognition.…”

Section: Related Workmentioning

confidence: 99%

Extending a communication service provider's operations management based on knowledge granules and aspects derived from imperfect information

Dragun

Bogunović

2019

Int J Communication

View full text Add to dashboard Cite

The core of a communication service provider's business revolves around servicerelated operations management, usually relying strongly on expert knowledge built inside the company. Knowledge representation in this environment inevitably requires addressing various domains. Team members working on common tasks bring domain diversity to their teams due to their various ontological areas of expertise. All team members must attain an acceptable level of knowledge regarding other domains to reach a team's desired level of effectiveness. This paper provides a novel way of linking divergent domain ontologies to facilitate and enrich service management in the communication service provider environment. The typical service provider infrastructure offers an extensive source of information for deriving knowledge regarding services, but the information is generally imperfect, inconsistent, and incomplete. Introducing a granular approach based on rough sets applicable to this imperfect information enables fractional management, which together with multiaspect formalisms enables the derivation of the specificity of a certain domain from a common source of knowledge without interference from other domains. A case study illustrates the implementation of an intelligent communication service and network management system based on the contexts used for assisting service strategies. The implementation empirically justifies the proposed approach.KEYWORDS aspects, imperfect information, knowledge granules, knowledge management, service operations management 1 | INTRODUCTION Communication service providers (CSPs) attempt to incorporate many disciplines into their daily service providing processes to differentiate themselves in the market. This incorporation involves broadening the set of standard telecomrelated domains by introducing new domains necessary to produce new content and to enrich existing portfolios. The final goal of these activities is to improve the CSP's service quality. However, despite many advantages of a multidisciplinary approach, stemming mostly from the fact that diversity results in greater versatility when providing services, substantial challenges exist under these conditions. Because introducing various disciplines requires bringing in experts from those disciplines to work together to provide the related services, functional teams covering all necessary domains

show abstract

A recommender system architecture for predictive telecom network management

Cited by 19 publications

References 13 publications

Test Recommendation for Service Validation in 5G Networks

Test Recommendation for Service Validation in 5G Networks

Managing and Optimizing Quality of Service in 5G Environments Across the Complete SLA Lifecycle

Extending a communication service provider's operations management based on knowledge granules and aspects derived from imperfect information

Contact Info

Product

Resources

About