東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Novel Routing in Data Center Networks.

Wang, Suzhen.

FindBook

Google Book

Amazon

博客來

Novel Routing in Data Center Networks.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Novel Routing in Data Center Networks./
作者:	Wang, Suzhen.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
面頁冊數:	119 p.
附註:	Source: Dissertations Abstracts International, Volume: 80-08, Section: A.
Contained By:	Dissertations Abstracts International80-08A.
標題:	Communication. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13837909
ISBN:	9780438852075

Novel Routing in Data Center Networks.
Wang, Suzhen.

Novel Routing in Data Center Networks. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 119 p.

Source: Dissertations Abstracts International, Volume: 80-08, Section: A.

Thesis (Ph.D.)--The Chinese University of Hong Kong (Hong Kong), 2018.

This item must not be sold to any third party vendors.

As computation continuously moves into the cloud and with the widespread use of cloud services, data centers have gained popularity. A typical data center has hundreds of thousands of servers, or even more. Due to the rapid growth of cloud computing, the scale of data centers continues to expand fast. Meanwhile, the underlying Data Center Networks (DCNs) are confronted with an unprecedented amount of traffic. This trend places great challenges on the design of high-performance DCNs, which is aimed for cost effectiveness, high scalability, high throughput, and low latency. Many existing DCNs adopt the fat-tree topology. In addition to scalability and high bisection bandwidth, fat-trees also provide a rich number of paths for every Source-Destination (S-D) pair, facilitating designs of load-balanced routing for DCNs. To further improve scalability and reduce deployment cost, variants of the Hypercube topology have emerged recently, such as BCube, DCell, and ExCCC. These topologies have properties of low degree, low diameter, and high scalability. Load-balanced routing design is another key to achieving desirable DCNs. For mega DCNs with a huge number of servers and switches, existing load balanced routing schemes face issues such as scalability, high overhead, and slow response to traffic dynamics and congested incomings. To solve these problems, we design a novel routing scheme for fat-tree DCNs. The new routing scheme takes a smart use of the topological features of fat-tree DCNs as well as the two-choice idea from Randomized Algorithm, and achieves significant improvements over existing routing schemes. Note that optical technologies based on Wavelength Division Multiplexing (WDM) are gaining popularity for DCNs due to their technological strengths such as low communication latency, low power consumption, and high link bandwidth. Motivated by this phenomenon, we make the first attempt to investigate the optical-routing performance of BCube DCN, and demonstrate that the BCube topology is desirable for all-optical DCNs.

ISBN: 9780438852075Subjects--Topical Terms:

524709
Communication.

Novel Routing in Data Center Networks.
LDR:03136nmm a2200325 4500 001 2208036
005 20190929184033.5
008 201008s2018 ||||||||||||||||| ||eng d
020 $a 9780438852075
035 $a (MiAaPQ)AAI13837909
035 $a AAI13837909
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Suzhen. $3 3435046
245 1 0 $a Novel Routing in Data Center Networks.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 119 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-08, Section: A.
500 $a Publisher info.: Dissertation/Thesis.
502 $a Thesis (Ph.D.)--The Chinese University of Hong Kong (Hong Kong), 2018.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a As computation continuously moves into the cloud and with the widespread use of cloud services, data centers have gained popularity. A typical data center has hundreds of thousands of servers, or even more. Due to the rapid growth of cloud computing, the scale of data centers continues to expand fast. Meanwhile, the underlying Data Center Networks (DCNs) are confronted with an unprecedented amount of traffic. This trend places great challenges on the design of high-performance DCNs, which is aimed for cost effectiveness, high scalability, high throughput, and low latency. Many existing DCNs adopt the fat-tree topology. In addition to scalability and high bisection bandwidth, fat-trees also provide a rich number of paths for every Source-Destination (S-D) pair, facilitating designs of load-balanced routing for DCNs. To further improve scalability and reduce deployment cost, variants of the Hypercube topology have emerged recently, such as BCube, DCell, and ExCCC. These topologies have properties of low degree, low diameter, and high scalability. Load-balanced routing design is another key to achieving desirable DCNs. For mega DCNs with a huge number of servers and switches, existing load balanced routing schemes face issues such as scalability, high overhead, and slow response to traffic dynamics and congested incomings. To solve these problems, we design a novel routing scheme for fat-tree DCNs. The new routing scheme takes a smart use of the topological features of fat-tree DCNs as well as the two-choice idea from Randomized Algorithm, and achieves significant improvements over existing routing schemes. Note that optical technologies based on Wavelength Division Multiplexing (WDM) are gaining popularity for DCNs due to their technological strengths such as low communication latency, low power consumption, and high link bandwidth. Motivated by this phenomenon, we make the first attempt to investigate the optical-routing performance of BCube DCN, and demonstrate that the BCube topology is desirable for all-optical DCNs.
590 $a School code: 1307.
650 4 $a Communication. $3 524709
650 4 $a Technical Communication. $3 1669287
650 4 $a Information science. $3 554358
690 $a 0459
690 $a 0643
690 $a 0723
710 2 $a The Chinese University of Hong Kong (Hong Kong). $b Information Engineering. $3 3180141
773 0 $t Dissertations Abstracts International $g 80-08A.
790 $a 1307
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13837909