Empowering managed service providers: decentralised AI-enabled monitoring in multi-tenant networks

Adeel Rafiq, Muhammad Zeeshan Shakir, David Gray, Julie Inglis, Fraser Ferguson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Downloads (Pure)

Abstract

Managing a multi-tenant network presents formidable challenges to managed service providers (MSPs) as they endeavour to provide exceptional service quality to clients scattered across diverse locations. These challenges are compounded by clients' stringent requirements to shield the identities of their network elements, preventing their exposure for centralised monitoring purposes. Consequently, the task of MSPs in overseeing geographically dispersed networks becomes more intricate due to the necessity of establishing separate real-time monitoring systems for each client. Moreover, the importance of visualising monitored data cannot be overstated, as it unveils invaluable patterns that illuminate service quality issues. Consequently, a monitoring tool equipped with a richly informative dashboard becomes indispensable for strategic planning and the delivery of top-tier services. Furthermore, the integration of AI -driven resource prediction enhances incident resolution capabilities by enabling proactive alert notifications. In response to these complex challenges, this research introduces an architectural solution centred around a data visualisation platform. This platform harnesses the power of a portable, decentralised AI-enabled real-time network monitoring tool custom-tailored for multi-tenant networks. The proposed approach adopts a pragmatic strategy that seamlessly integrates multiple open-source modules across geographically dispersed networks. The result is nothing short of remarkable compared with the manual approach, with network element downtime experiencing a remarkable 95% reduction, and incident resolution seeing a noteworthy 90 % reduction. This transformative impact directly benefits service desk professionals and network design engineers alike of MSPs.
Original languageEnglish
Title of host publicationBig Data and Smart Computing Conference 2024
EditorsHerwig Unger, Jinseok Chae, Young-Koo Lee, Christian Wagner, Chaokun Wang, Mehdi Bennis, Mahasak Ketcham, Young-Kyoon Suh, Hyuk-Yoon Kwon
PublisherIEEE
Pages124-130
Number of pages7
ISBN (Electronic)9798350370027
ISBN (Print)9798350370034
DOIs
Publication statusPublished - 18 Feb 2024
Event2024 IEEE International Conference on Big Data and Smart Computing - The Sukosol Hotel, Bangkok, Thailand
Duration: 18 Feb 202421 Feb 2024
https://www.bigcomputing.org/conf2024/

Publication series

NameIEEE Conference Proceedings
PublisherIEEE
ISSN (Print)2375-933X
ISSN (Electronic)2375-9356

Conference

Conference2024 IEEE International Conference on Big Data and Smart Computing
Abbreviated titleBIGCOMP
Country/TerritoryThailand
CityBangkok
Period18/02/2421/02/24
Internet address

Keywords

  • multi-tenant network
  • monitoring
  • decentralisation
  • machine learning
  • artificial intelligence

Fingerprint

Dive into the research topics of 'Empowering managed service providers: decentralised AI-enabled monitoring in multi-tenant networks'. Together they form a unique fingerprint.

Cite this