Show simple item record

AuthorChkirbene, Zina
AuthorHamila, Ridha
AuthorAl-Dweik, Arafat
AuthorKhattab, Tamer
Available date2024-03-04T04:39:56Z
Publication Date2023-01-01
Publication NameIEEE Access
Identifierhttp://dx.doi.org/10.1109/ACCESS.2023.3325321
CitationZ. Chkirbene, R. Hamila, A. Al-Dweik and T. Khattab, "Advancing Data Center Networks: A Focus on Energy and Cost Efficiency," in IEEE Access, vol. 11, pp. 117656-117669, 2023, doi: 10.1109/ACCESS.2023.3325321. keywords: {Switches;Topology;Network topology;Servers;Data centers;Costs;Scalability;Energy consumption;Data center;network topology;flexible connection;energy consumption;infrastructure cost},
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85174854418&origin=inward
URIhttp://hdl.handle.net/10576/52612
AbstractData centers serve as the backbone for cloud computing, enterprise services, and infrastructure-based offerings. One area of ongoing research in data center networking focuses on innovating new topologies for large-scale node connectivity. These topologies must incorporate fault-tolerant and efficient routing algorithms. Consequently, the data center network topology must dynamically adapt to ever-changing application requirements. While traditional topology designs often emphasize scalability, they are typically limited by the necessity for dedicated switches to manage server connections. The development of software technologies that distinguish server and switch roles offers a unique opportunity to reconsider design priorities, paving the way for a more balanced assessment of scalability, energy efficiency, and infrastructure costs. Moreover, certain network topologies fail to be cost-effective due to their structural intricacies, often requiring far more node connections than those that are practically necessary. To address these challenges, we introduce VacoNet: a new flexible data center network topology that organizes nodes into structurally similar clusters, interconnected by a novel physical structure algorithm. Boasting high bisection bandwidth, VacoNet delivers robust network capacity, even when encountering bottlenecks. Furthermore, to connect a given set of nodes, VacoNet uses a minimal number of cables and switches, thereby drastically reducing both infrastructure costs and energy consumption. Simulation results show that VacoNet can reduce error rates by 20% and slash infrastructure costs by 70% compared to existing solutions. Additionally, it performs tasks 30% faster, underscoring its superior performance.
Sponsor10.13039/501100004252-Qatar University Internal (Grant Number: IRCC-2023-237) 10.13039/100019779-Qatar National Library
Languageen
PublisherIEEE
SubjectData center
energy consumption
flexible connection
infrastructure cost
network topology
TitleAdvancing Data Center Networks: A Focus on Energy and Cost Efficiency
TypeArticle
Volume Number11
ESSN2169-3536
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record