現今市面上常見的網路流量分析系統，大多採用系統模擬或是以Benchmark的方式來評估其效能，但以目前的網路複雜度與應用的多元性而言，其模擬結果之真實性備受質疑。因此若測試系統為真實的網路設備，其資料分析的結果勢必能更貼近真實的網路架構。此種方式將有助於萃取真實世界的網路特性，並可在此平台上提出各種演算法驗證其效能與實用性。但一般使用者在取得應用服務的時候常發生不當的應用服務佔用大量網路頻寬等問題，使得使用者需求的即時傳輸應用如VoIP或是多媒體影音串流等服務只能使用剩餘的頻寬，造成服務品質低落或傳輸效能不佳等影響，以至於服務無法符合使用者的期望，因此如何有效的管理各應用之服務品質是即需解決的議題。

其問題的主要原因是一般網管設備的內部軟體架構所提供的資源大多是封閉性的平台，因此在網路教學與研究上僅能於應用層做微調的設計開發，且無法提供底層協定的完整支援。有鑑於此，本研究利用NetFPGA硬體平台抓取真實封包的能力搭配史丹佛大學所提出的OpenFlow網路虛擬化架構，以建構一個完整的開發環境。本系統從交換器將各種封包分類過濾後並標記所屬的應用類型，再經由Monitor Agent模組彙整Traffic Monitor模組和Bandwidth Monitor模組所提供的資訊建成一個Record Table，使本研究設計之管理機制能夠獲得QoS參數，並藉由可調整的QoS處理策略，進行網路流量的控制與調整。

本研究所提出的機制架構主要是針對QoS策略的解析，以取得使用者自訂的服務要求，並確保當網路服務品質降低時，使用者要求的服務能持續且順暢。本研究提出的可調適QoS機制利用此方式建構一個區域網路虛擬環境，並依使用者定義的服務策略測試其實際的運作效能。為求實際本研究設定不同要求的受測對象(Bob和Alice)，因此當網路的頻寬使用率超過25%時，即進行策略的解析並依使用者的要求維持特定服務的存取行為。由結果得知，使用者填入策略的服務會持續運作，但未寫入的服務就會被阻擋在外面，以提高使用者存取服務的頻寬。

Current methods of analyzing network data flow such as simulations and benchmark pattern analysis are widely considered inadequate for examining complex or diverse network applications. Compared to these virtual verification methods, network-based verification systems offer improved accuracy and precision. However, general users who get the service will bring many potential problems. For instance, improper services occupy most of the bandwidth so that the instant transmission programs like VoIP and multimedia streaming can only be transmitted by finite bandwidth. This can bring about some negative effects such as low-quality transmission. Therefore, how to manage the quality of service efficiently is the most important.

Commoditized networking equipment cannot provide actual benefits depend on management services. The architectures of such equipment are often closed and forming islands of incompatible technologies, which prevent developers from implementing customized network protocols in network devices. For network education and research, such resources are limited to do partial development in the application layer, and they are inadequate for low-level protocols. Therefore, this work proposes the complete control of network flow data to obtain actual packets by combining the NetFPGA platform with OpenFlow. Novel network virtualization architecture is proposed for comprehensive network management. The system receives the marked packets from a switch. The monitor agent acquires information from traffic. The bandwidth monitor modules construct the record table providing information for the adaptive QoS strategy. The proposed architecture can then provide network traffic control and adjustment.

Because the proposed mechanism mainly parses the user-defined QoS policy, it maintains uninterrupted service when user-requested network conditions deteriorate. The proposed adaptive QoS mechanism is using this method to construct a virtual LAN environment and user-defined service policy by testing the effectiveness of its actual operation. The study subjects were Bob and Alice; each defines its own policy. It will parse the policy and maintain the transmission of user requirements services when bandwidth usage exceeds 25%. By the results, when used for a period of time, users will continue to operate the services requested, and the other service will be terminated.

[1] NetFPGA official website, http://www.netfpga.org/
[2] NetFPGA fourm, http://forum.netfpga.org/
[3] J. W. Lockwood, N. McKeown, G. Watson, G. Gibb, P. Hartke, J. Naous, R. Raghuraman, and J. Luo. “NetFPGA—An Open Platform for Gigabit-Rate Network Switching and Routing,“ Proceedings of the IEEE International Conference on Microelectronic Systems Education, pp. 160–161, Washington, DC, USA, June 2007.
[4] M. Ciesla, V. Sivaraman and A. Seneviratne. “URL Extraction Project Foswiki Page,” http://netfpga.org/foswiki/bin/view/NetFPGA/OneGig/URL
[5] Jad Naous, David Erickson, Adam Covington, Guido Appenzeller, and Nick McKeown, “Implementing an OpenFlow Switch on the NetFPGA platform,” Proceedings of the 4th ACM/IEEE Symposium on Architectures for Networking and Communications Systems, San Jose, CA, USA, pp. 1-9, November 6-7, 2008.
[6] J.W. Lockwood, N. McKeown, G. Watson, G. Gibb, P. Hartke, J. Naous, R. Raghuraman and J. Luo, “NetFPGA: An Open Platform for Teaching How to Build Gigabit-Rate Network Switches and Routers,” Proceedings of the IEEE Transactions on Education, San Diego, CA, Vol. 51, pp. 364-369, Jun. 2007.
[7] J. Naous, G. Gibb, S. Bolouki and N. McKeown. “NetFPGA: Reusable Router Architecture for Experimental Research,” Proceedings of the PRESTO, New York, NY, USA, pp.1-7, Aug. 22, 2008.
[8] Stanford University, Pee-Wee OSPF Protocol Details. (yuba.stanford.edu/cs344public/docs/pwospfref.txt.)
[9] OpenFlow website, http://www.OpenFlowSwitch.org
[10] N. McKeown, T. Anderson, H. Balakrishnan, G. Parulkar, L. Peterson, J. Rexford, S. Shenker and J. Turner, “OpenFlow: Enabling Innovation in Campus Networks,” Proceedings of the ACM SIGCOMM Computer Communication Review, Vol. 38, pp. 69-74, March 14, 2008.
[11] OpenFlow Switch Specification, Version 1.0.0
[12] M.P. Mateo, OpenFlow Switching Performance, Master Thesis, Politecnico Di Torino, July 2009.
[13] NOX Manual, http://noxrepo.org/manual/index.html
[14] N. Gude, T. Koponen, J. Pettit, B. Pfaff, M. Casado, N. McKeown and S. Shenker, “NOX: Towards an Operating System for Networks,” ACM SIGCOMM Computer Communication Review, Vol. 38, pp. 105-110, July 2008.
[15] K.K. Yap, M. Kobayashi, D. Underhill, S. Seetharaman, P. Kazemian and N. McKeown, “The Stanford OpenRoads Deployment,” Proceedings of the 4th ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation and Characterization, pp.59-66, September 2009.
[16] OpenFlow AP with PC Engine.
http://www.openflowswitch.org/wk/index.php/OpenFlow_AP_with_PC_Engine.
[17] FlowVisor, http://www.openflowswitch.org/wk/index.php/FlowVisor.
[18] Braden, Clark and Shenker, Integrated Services Architecture, RFC 1633 IETF, June 1994.
[19] Blake, “Architecture for Differentiated Services”, RFC 2475, Dec 1998.
[20] S. Sen, O. Spatsheck and D. Wang, “Accurate, scalable In-Network Identification of P2P Traffic Using Application Signatures,” Proceedings of the 13th International World Wide Web Conference, pp.512-521, NY, USA, May 2004.
[21] L. Bin, L. Qhitang and L. Zhanchun, “Traffic Measurement of Bittorrent System Based on Netfilter,” Proceedings of the 2006 International Conference on Computational Intelligence and Security, pp.1470-1474, February 2006.
[22] A. Madhukar and C. Williamson, “A Longitudinal Study of P2P Traffic Classification,” Proceedings of the 14th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, 2007.
[23] T. Karagiannis, A. Broido, N. Brownlee, K. Claffy and M. Faloutsos “Is P2P Dying or just Hiding?” Proceedings of the IEEE Globecom- Global Internet and Next Generation Networks, Dallas, Texas, USA, 29 Nov - 3 Dec, 2004.
[24] T. Karagiannis, D. Papagiannaki and M. Faloutsos “BLINC: Multilevel Traffic Classification in the Dark” ACM SIGCOMM Computer Communication Review 35 (4), pp. 229-240, August 2005.
[25] T. Karagiannis, A. Broido, M. Faloutsos and K.C. Claffy, “Transport Layer Identification of p2p Traffic,” Proceedings of the 2004 ACM SIGCOMM Internet Measurement Conference, IMC, pp. 121-134, 2004.
[26] IPP2P, http://www.ipp2p.org
[27] L7-filter, http://l7-filter.sourceforge.net
[28] Netfilter Project, http://www.netfilter.org.
[29] R. Russell and H. Welte, “Linux Netfilter Hacking HOWTO“, http://www.netfilter.org/documentation/HOWTO/netfilter-hacking-HOWTO.htm l, 2002.
[30] N. Lin and M. Qi, “A QoS Model of Next Generation Network based on MPLS,” Proceedings of IFIP International Conference on Network and Parallel Computing Workshops, pp. 915-919, 2007.
[31] D. Zhang and D. Ionescu, “QoS Performance Analysis in Deployment of DiffServ-aware MPLS Traffic Engineering,” Proceedings of the 8th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing, pp.963-967, August 2007.
[32] J. Salim, H. Khosravi, A. Kleen and A. Kuznetsov, Linux Netlink as an IP Services Protocol, RFC 3549 IETF, July 2003.
[33] M. Casado, M. J. Freedman, J. Pettit, J. Luo, N. McKeown and S. Shenker, “Ethane: Taking Control of the Enterprise,” Proceedings of the ACM SIGCOMM Conference on Computer Communications, Vol. 37, pp. 1-12, 2007.