隨著雲端應用服務和資料存取的需求日益增加，傳統網路的架構越來越不敷使用，同時，為了滿足資料中心網路流量巨大的需求，如何妥善管理整個資料中心網路顯得極為重要，而新興的軟體定義網路架構可改善傳統網路傳輸效率與靈活性不佳等問題，軟體定義網路的特點在於網管人員可自由操控封包傳輸的行為，而在資料中心網路流量甚大的情況下，此技術極為適合應用在此一環境中；本篇論文主要透過此技術，針對資料中心網路提出一套負載平衡機制，讓控制器即時監控網路中封包流量的情況，若達到臨界值，即啟動負載平衡機制，並改變資料流的傳輸路徑，以達到負載平衡的效果；而我們的演算法主要為動態調整資料流路徑，同時考慮OpenFlow路由表大小(Flow table size)的限制，並且利用OpenFlow組表(Group table)來達到分散流量的效果，此外，我們還會根據網路流量的情況，動態調整控制器詢問OpenFlow Switch資訊的時間間隔，以減少其處理的封包數量，根據模擬結果，在資料中心網路的環境下，我們的方法可以達到負載平衡的效果，並有效提升網路頻寬使用率，避免網路壅塞的情況，且減少控制器的負擔。

As the demand for cloud services and data intensive access applications increase, the traditional network architecture becomes inadequate. Meanwhile, it is important to efficiently manage a data center network, so as to satisfy the demand of large volume of traffic. The emerging software-defined networking (SDN) can address the above problem by allowing a network administrator to control packet transmissions flexibly. In this thesis, we propose a load-balanced mechanism which can get the real-time information about the network status in order to balance network load in a data center network. We adaptively change routing paths of flows and balance the amount of traffics among different links. Besides, we dynamically adjust the time period that the controller request the OpenFlow switches status, so as to decrease the number of packets required to be processed by the controller. According to the simulation results, our method improves throughput and bandwidth utilization, resolves the network congestion problem, and also reduces the controller’s load, which verifies its effectiveness.

論文審定書 i
致謝 ii
摘要 iii
Abstract iv
目錄 v
圖次 vii
表次 ix
第一章 緒論 1
1.1 簡介 1
1.2 論文研究動機與目的 3
1.3 論文貢獻與文章架構 5
第二章 研究背景 6
2.1 SDN網路架構 6
2.2 OpenFlow技術 7
2.3 RYU 10
2.4 OpenFlow Switch與Controller連線過程 11
2.5 資料中心網路 14
第三章 相關文獻探討 16
3.1 負載平衡技術 16
3.1.1 伺服器負載平衡 16
3.1.2 網路負載平衡 18
3.2 Flow Table Reduction技術 20
第四章 問題定義 22
第五章 系統架構與研究方法 24
5.1 建立表格 25
5.2 確認連線狀態 28
5.3 計算負載平衡參數 29
5.4 負載平衡策略 32
5.5 Polling Time Period調整機制 36
第六章 實驗結果 38
6.1 觸發負載平衡策略之臨界值實驗 39
6.2 Uniform Traffic Pattern實驗結果 40
6.3 Hot-spot Traffic Pattern實驗結果 45
第七章 結論以及未來展望 50
7.1 結論 50
7.2 未來展望 50
參考文獻 51

[1] International Organization for Standardization. [Online]. Available: https://www.iso.org/home.html.
[2] N. McKeown, “Software-Defined Networking”, IEEE INFOCOM Keynote Talks, vol. 17, no. 2, pp. 30-32, 2009.
[3] A. Craig, B. Nandy, I. Lambadaris, and P. Ashwood-Smith, “Load Balancing for Multicast Traffic in SDN Using Real-time Link Cost Modification,” IEEE International Conference on Communications, pp. 5789-5795, 2015.
[4] D. Kreutz, F. M. V. Ramos, P. E. Verissimo, C. E. Rothenberg, S. Azodolmolky, and S. Uhlig, “Software-Defined Networking: A Comprehensive Survey,” Proceedings of the IEEE, vol. 103, no. 1, pp. 14-76, 2015.
[5] T. V. Tran and H. Ahn, “A Network Topology-aware Selectively Distributed Firewall Control in SDN,” International Conference on Information and Communication Technology Convergence, pp. 89-94, 2015.
[6] M. Al-Fares, A. Loukissas, and A. Vahdat, “A Scalable, Commodity Data Center Network Architecture,” ACM SIGCOMM Computer Communication, vol. 38, no. 4, pp. 63-74, 2008.
[7] H. Kim and N. Feamster, “Improving Network Management with Software Defined Networking,” IEEE Communications Magazine, vol. 51, no. 2, pp. 114-119, 2013.
[8] J. Yu and I. A. Ajarmeh, “An Empirical Study of the NETCONF Protocol,” International Conference on Networking and Services, pp. 253-258, 2010.
[9] Y. Han, S. Ryu, Y. Suh, and J. W. Hong, “Design and implementation of LISP controller in ONOS,” IEEE NetSoft Conference and Workshops, pp. 417-422, 2016.
[10] N. McKeown, G. Parulkar, T. Anderson, L. Peterson, H. Balakrishnan, J. Rexford, S. Shenker, and J. Turner, “OpenFlow: Enabling Innovation in Campus Networks,” ACM SIGCOMM Computer Communication, pp. 69-74, 2008.
[11] Open Networking Foundation. [Online]. Available: https://www.opennetworking.org.
[12] RYU SDN Framework. [Online]. Available: https://osrg.github.io/ryu.
[13] T. Desai and J. Prajapati, “A Survey Of Various Load Balancing Techniques And Challenges In Cloud Computing,” International Journal of Scientific & Technology Research, vol. 2, no. 11, pp. 158-161, 2013.
[14] D. Zeng, G. Yang, L. Gu, S. Guo, and H. Yao, “Joint Optimization on Switch Activation and Flow Routing Towards Energy Efficient Software Defined Data Center Networks,” IEEE International Conference on Communications, pp. 1-6, 2016.
[15] S. Sharma, S. Singh, and M. Sharma, “Performance Analysis of Load Balancing Algorithms,” International Journal of Computer, Electrical, Automation, Control and Information Engineering, vol. 2, no. 2, pp. 367-370, 2008.
[16] R. Lee and B. Jeng, “Load-Balancing Tactics in Cloud,” International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, pp. 447-454, 2011.
[17] H. Zhang and X. Guo, “SDN-based Load Balancing Strategy for Server Cluster,” International Conference on Cloud Computing and Intelligence Systems, pp. 662-667, 2015.
[18] M. Qilin and S. WeiKang, “A Load Balancing Method Based on SDN,” International Conference on Measuring Technology and Mechatronics Automation, pp. 18-21, 2015.
[19] J. Liu, J. Li, G. Shou, Y. Hu, Z. Guo, and W. Dai, “SDN Based Load Balancing Mechanism for Elephant Flow in Data Center Networks,” International Symposium on Wireless Personal Multimedia Communications, pp. 486-490, 2014.
[20] D. Adami, G. Antichi, R. Garroppo, S. Giordano, and A. Moore, “Towards an SDN Network Control Application for Differentiated Traffic Routing,” International Conference on Communications, pp. 5827-5832, 2015.
[21] M. Ramdhani, S. Hertiana, and B. Dirgantara, “Multipath Routing with Load Balancing and Admission Control in Software-Defined Networking (SDN),” International Conference on Information and Communication Technology, pp. 1-6, 2016.
[22] D. Adami, S. Giordano, M. Pagano, and G. Portaluri, “A novel SDN Controller for Traffic Recovery and Load Balancing in Data Centers,” International Workshop on Computer Aided Modelling and Design of Communication Links and Networks, pp. 77-82, 2016.
[23] H. Long, Y. Shen, M. Guo, and F. Tang, “LABERIO: Dynamic Load-balanced Routing in OpenFlow-enabled Networks,” International Conference on Advanced Information Networking and Applications, pp. 290-297, 2013.
[24] Y. L. Lan, K. Wang, and Y. H. Hsu, “Dynamic Load-balanced Path Optimization in SDN-based Data Center Networks,” International Symposium on Communication Systems, Networks and Digital Signal Processing, pp. 1-6, 2016.
[25] B. Leng, L. Huang, X. Wang, H. Xu, and Y. Zhang, “A Mechanism for Reducing Flow Tables in Software Defined Network,” IEEE International Conference on Communications, pp. 5302-5307, 2015.
[26] H. Li, S. Guo, C. Wu, and J. Li, “FDRC: Flow-Driven Rule Caching Optimization In Software Defined Networking,” IEEE International Conference on Communications, pp. 5777-5782, 2015.
[27] L. Zhang, S. Wang, S. Xu, R. Lin, and H. Yu, “TimeoutX: An Adaptive Flow Table Management Method in Software Defined Networks,” IEEE Global Communications Conference, pp. 1-6, 2015.
[28] Flowgrammable Organization. [Online]. Available: http://flowgrammable.org/
[29] Mininet. [Online]. Available: http://mininet.org/
[30] OpenvSwitch. [Online]. Available: http://openvswitch.org/
[31] Wireshark. [Online]. Available: https://www.wireshark.org/