跳到主要內容

臺灣博碩士論文加值系統

(18.97.9.172) 您好!臺灣時間:2025/02/14 03:12
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:邱啟宏
研究生(外文):Ci-Hung Ciou
論文名稱:在軟體定義網路中處理多播標籤的分群演算法
論文名稱(外文):Clustering Algorithm for Multicast Labelling in SDN
指導教授:王丕中
口試委員:紀光輝張弘毅易志偉
口試日期:2017-07-28
學位類別:碩士
校院名稱:國立中興大學
系所名稱:資訊工程學系所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2017
畢業學年度:105
語文別:英文
論文頁數:31
中文關鍵詞:多播標籤路由器啟發式演算法軟體定義網路
外文關鍵詞:Multicast labelrouterheuristic algorithmSDN
相關次數:
  • 被引用被引用:0
  • 點閱點閱:177
  • 評分評分:
  • 下載下載:7
  • 收藏至我的研究室書目清單書目收藏:1
多播是一種有效率的傳輸方式,藉由一對多的傳輸節省下大量的頻寬資源,多播必須仰賴網路上路由器的支援才能使用,路由器將一個個封包複製成多個傳送到目的地,然而路由器在處理多播的過程中,必需透過local multicast labels (LMLs)得知要將封包複製到哪些埠,LML一般是以bitmap的形式表示,路由器有多少埠LML的長度就有多長,但是這樣的表示方法在大型路由器(128埠以上)上會產生問題,此外,路由器要處理大量的多播群組也必須有對應的機制來存放LML的資訊。Greedy Row-Clustering使用貪婪的方式為每個LML分群,並利用supercast的概念取代多播,但卻沒有針對不同流量大小的多播群組做特定的處理, 如今有了Software Defined Networking (SDN)的網路架構下,可以完整取得每個流(Flow)的數值,因此在本篇論文中,我們先分析多播群組的流量資訊,並且改善Greedy Row-Clustering的演算法,優先的處理大流量的多播群組,並且讓大流量的多播群組可以利用各自分配的空間進行分群,這樣的作法除了讓整體的頻寬浪費有效降低以外,在運算時間上也得到了很好的改善。
Multicast is a one-to-many transmission, which can efficiently save bandwidth resources . Multicast must rely on the support of routers in the network, where the router can replicate a packet to multiple receivers in the same group. However, the routers must store the local multicast labels (LMLs) for packet replication of different ports when processing multicast traffic. LMLs are generally in the form of bitmaps. The length of the LMLs is equal to the number of ports, but long LMLs causes a storage problem for large routers with 128 or more ports. In addition, the router which has a large number of multicast groups must also needs an efficient mechanism to store LMLs.

Greedy Row-Clustering (GRC) stores multiple LMLs in a cluster with a greedy algorithm based on the idea of supercast, but the scheme does not consider the overhead of clustering multicast groups with different flow size. In the emerging architecture of software defined networking (SDN), we can obtain the size of each flow. Accordingly, we will analysis the flow information of each multicast group, and improve the performance of GRC for multicast groups with large flows. Our scheme reserves memory space for different flow sizes, and clusters groups into the allocated spaces based on their sizes. The experimental results show that our algorithm not only reduces the overall bandwidth waste, but also improves the computing time.
摘要 i
Abstract ii
Table of Contents iii
List of Tables iv
List of Figures v
Chapter 1 Introduction 1
Chapter 2 Related work 5
2.1 SDN 5
2.2 Multicast labelling and Greedy Row-Clustering 5
Chapter 3 Proposed Algorithm 9
3.1 Problem Statement 9
3.2 Heuristic Algorithm based on Greedy Row-Clustering 10
3.3 Traffic Update 16
Chapter 4 Performance Evaluation 19
Chapter 5 Conclusions 29
References 30
[1]Cisco, “The Zettabyte Era—Trends and Analysis,” White Paper, 2013.
[2]N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner. “OpenFlow: Enabling Innovation in Campus Networks”, SIGCOMM Comput. Commun. Rev., 38:69–74, March 2008.
[3]Lei Huang, Xiaoli Zhi, Qiang Gao, Samina Kausar, and Shengan Zheng, “Design and implementation of multicast routing system over SDN and sFlow,” in 2016 8th IEEE International Conference on Communication Software and Networks (ICCSN). IEEE Conference Publications, 2016, pp. 524 – 529.
[4]M. Yu, L. Jose, and R. Miao. “Software defined traffic measurement with opensketch”, In Proc. of NSDI, 2013.
[5]P. Phaal, “sFlow Specification Version 5,” July 2004, Available: http://www.sflow.org/sflow_version_5.txt, (February 18, 2016), pp.1-48.
[6]Jingguo Ge, Hanji Shen, Yuepeng E, Yulei Wu, and Junling You, “An OpenFlow-Based Dynamic Path Adjustment Algorithm for Multicast Spanning Trees”, Trust, Security and Privacy in Computing and Communications (TrustCom), IEEE International Conference on, pp. 1478-1483, 2013.
[7]Askash Iyer, Praveen Kumar, and Vijay Mann, “Avalanche: Data Center Multicast using Software Defined Networking,” Communication Systems and Networks (COMSNETS), 2014 Sixth International Conference on, 2014.
[8]Tim Humernbrum, Bastian Hagedorn, and Sergei Gorlatch, “Towards Efficient Multicast Communication in Software-Defined Networks”, Distributed Computing Systems Workshops (ICDCSW), 2016.
[9]Punit Bhargava, Sriram C. Krishnan and Rina Panigrahy, “Efficient Multicast on a Terabit Router”, 12th Annual IEEE Symposium on High Performance Interconnects, August 2004.
[10]F. M. Chiussi, A. FranciniM. Ajmone Marsan, G. Galante, and E. Leonardi, “Efficient Multicast Support in Large IP Routers”, Global Telecommunications Conference, 2002.
[11]Yufeng Li, Julong Lan, Han Qiu, Peng Yi, and Fengsen Deng, “Efficient and Lossless Multicast Support in Large Routers”, Communication Technology, 2006.
[12]Hyunwoo Nam, Kyung-Hwa Kim, Henning Schulzrinne, “QoE matters more than QoS:Why people stop watching cat videos”, in IEEE International Conference on Computer Communications, April 2016.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top