近年來雲端計算越來越受歡迎，BCube是其中一個新興的資料中心架構，然而在BCube拓樸上找一個多點傳播樹是一個NP困難 (NP-Hard)的史坦納樹問題(Steiner tree problem)。我們提出一個啟發式的演算法，Resource-Saving Multicast Tree (RSMT)演算法。RSMT的目標為找到一個路徑高重複使用的多點傳播樹。我們設計了一個貪心(Greedy)的演算法，每次挑選出一個目前最佳的接收者(Receiver)並將此接收者連接上目前的多點傳播樹。當動態接收者加入或離開，造成多點傳播樹沒有效率的時候，RSMT也可以重新產生新的多點傳播樹。 實驗結果顯示，我們可以找到一個多點傳播樹擁有較已經存在的方法更低的成本與更高的效能。再則，經由實驗，我們觀察到額外的延遲時間 (Extra delay-time)在小規模的BCube拓樸以及小規模的多點傳播群組裡有較佳的效率。

In recent years, cloud computing becomes more and more popular. BCube is one of the novel architecture proposed for data centers. However, finding a multicast tree in BCube is a Steiner tree problem which is an NP-hard problem. We propose a heuristic algorithm, Resource-Saving Multicast Tree (RSMT) algorithm. The goal of RSMT is to find a multicast tree with high path reusability for a multicast group. We design a greedy method that picks a local optimal receiver and union it to multicast tree at a time. RSMT also can handle the dynamic joining and leaving of receivers by reconstructing the multicast tree when it is no longer efficient. The experiment result shows that we can find a multicast tree with lower communication cost and higher throughput compared to existed solutions. Furthermore, we observe that we can sacrifice some delay-time of some receivers to reduce the total communication cost of a multicast tree for small BCube with small multicast group size.

Chapter 1 Introduction 1
Chapter 2 Preliminary 4
2.1 Multicast in Data Center Networks 4
2.2 BCube Data Center Networks Topology 5
2.3 Problem Formulation 6
Chapter 3 Multicast Tree Algorithm 9
3.1 Resource-Saving Multicast Tree algorithms (RSMT) 9
3.2 Dynamical Receivers Joining/Leaving 18
Chapter 4 Performance Evaluation 19
4.1 Threshold of RSMT Algorithm 19
4.2 Single Multicast request 21
4.3 Multiple Multicast requests 23
4.4 Network Size Variation 24
4.5 Multicast Reconstruction 25
Chapter 5 Conclusion 28
References 29

[1] Google Compute Engine. http://cloud.google.com/products/compute-engine.
[2] Microsoft Windows Azure. http://www.windowsazure.com/en-us/solutions/infrastructure/
[3] Amazon EC2 Spot Instance. http://aws.amazon.com/ec2/spot-instances/
[4] ONF Market Education Committee. “Software-Defined Networking: The New Norm for Networks,” ONF White Paper, Palo Alto, US: Open Networking Foundation, 2012.
[5] N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker, and J. Turner, “OpenFlow: Enabling Innovation in Campus Networks,” in ACM SIGCOMM Computer Communication Review, 2008
[6] Urs Hölzle, “OpenFlow @ Google,” keynote speech in the second annual Open Networking Summit, 2012.
[7] S. Jain, A. Kumar, S. Mandal, J. Ong, L. Poutievski, A. Singh, S. Venkata, J. Wanderer, J. Zhou, M. Zhu, J. Zolla, U. Hölzle, S. Stuart and A. Vahdat, “B4: Experience with a Globally-Deployed Software Defined WAN,” Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM. ACM, 2013.
[8] M. Al-Fares, A. Loukissas, and A. Vahdat. “A Scalable, Commodity Data Center Network Architecture,” in SIGCOMM, 2008.
[9] C. Guo, H. Wu, K. Tan, L. Shiy, Y. Zhang, and S. Lu. “Bcube: A high performance, server-centric network architecture for modular data centers,” In SIGCOMM, 2009.
[10] A. Greenberg, J. Hamilton, N. Jain, S. Kandula, C. Kim, P. Lahiri, D. Maltz, P. Patel, and S. Sengupta. “VL2: A Scalable and Flexible Data Center Network,” in Proceedings of the ACM SIGCOMM 2009 Conference on Data Communication (SIGCOMM’09), Barcelona, Spain, Aug. 2009.
[11] R. Mysore, A. Pamboris, N. Farrington, N. Huang, P. Miri, S. Radhakrishnan, V. Subramanya, and A. Vahdat. “PortLand: A Scalable Fault-Tolerant Layer 2 Data Center Network Fabric,” in Proceedings of the ACM SIGCOMM 2009 Conference on Data Communication (SIGCOMM’09), Barcelona, Spain, Aug. 2009.
[12] V. Liu, D. Halperin, A. Krishnamurthy, and T. Anderson. “F10: A Fault-Tolerant Engineered Network,” in Proceedings of the 10th USENIX Conference on Networked Systems Design and Implementation (NSDI’13), Lombard, Illinois, USA, Apr. 2013.
[13] C. Guo, H. Wu, K. Tan, L. Shi, Y. Zhang, S. Lu. “DCell: a scalable and fault-tolerant network structure for data centers,” ACM SIGCOMM Computer Communication Review, 2008.
[14] A. Singla, C. Hong, L. Popa, P. Godfrey, “Jellyfish: networking data centers randomly,” in 3rd USENIX conference on Hot topics in cloud computing, Portland, 2012.
[15] J. Dean and S. Ghemawat, “MapReduce: Simplified Data Processing on Large Clusters,” 6th Symposium on Operating System Design and Implementation (OSDI 2004), December 2004.
[16] S. Ghemawat, H. Gobioff, and S.-T. Leung, “The Google File System,” ACM SIGOPS Operating Systems Review, 2003.
[17] M. Imase and B. M. Waxman, "Dynamic Steiner tree problem," SIAM Journal on Discrete Mathematics, vol. 4, no. 3, pp. 369-3S4, 1991.
[18] D. Li, J. Yu, J. Yu, and J. Wu, “Exploring efficient and scalable multicast routing in future data center networks,” in Proc. IEEE INFOCOM, pp. 1368–1376, April, 2011.
[19] Z. Guo, J. Duan and Y. Yang, “On-Line Multicast Scheduling with Bounded Congestion in Fat-Tree Data Center Networks,” IEEE Journal on Selected Areas in Communications, vol. 32, no. 1, January, 2014.
[20] A. Iyer, P. Kumar and V. Mann, “Avalanche: Data Center Multicast using Software Defined Networking,” Sixth International Conference on Communication Systems and Networks (COMSNETS), 2014.