近年隨著網路技術的進步，影音串流的應用已逐漸補及開來。但是要達到多人的即時影音串流是相當不容易的事，原因是在於舊有的網路架構下，難以即時掌握整個網路的狀況，進而做更進一步的分配及管理。近年來，軟體定義的網路架構帶來了新的選擇，透過它，使得網路管理變得容易許多，更重要的是可以更方便取得整個網路上的資訊。我們提出了一套機制，目的是為了讓多使用者的情況下，達到最小的延遲，進而有更好的體驗。根據使用者的資訊，像是緩存區的大小或是頻寬的大小，伺服器可以調整片段的大小，並且如果使用者的緩存狀況很好的話，可以加速傳輸;另外，若是有多位使用者的情形，也可以整體調整狀況，已達到多人最佳的使用體驗。

Video streaming applications have become a popular way to deliver media contents increasingly since Internet changes itself fast with the time, not only hardware but software. However, it is difficult to address real-time streaming of multimedia over Internet because of the lack of overall network resources, therefore it is hard to dealing with steaming to multi-users. Software-Defined-Networking (SDN) is an emerging architecture, which helps to handle this issue mentioned previously. This research proposes a mechanism that helps to deal with this issue. Our mechanism focuses on the user information, including user buffer size or current bandwidth, to improve Quality of Service (QoS), such as transmission latency. The mechanism consists of two main elements, including predicting module and scheduling module. Predicting module can figure out the time stamp of latency occurred; scheduling module can create the schedule according the deadline of each segment to reduce latency. At last, this research uses Mininet to simulate this work. The result shows that this methodology has a good performance and reduce latency well.

[1] “Minutes of Viewed Live Stream Video”, http://www.businessinsider.com/chart-of-the-day-live-streaming-video-2010-9, retrieved on March 2014.
[2] “Business Insider”, http://www.businessinsider.com/chart-of-the-day-live-streaming-video-2010-9, retrieved on March 2014.
[3] “Quality of Service (QoS)”, http://www.cisco.com/c/en/us/products/ios-nx-os-software/quality-of-service-qos/index.html, retrieved on May 2014.
[4] “Take Control of Your Traffic - A New Approach to Software Defined Networking”, http://www.mellanox.com/sdn/, retrieved on March 2014.
[5] “Software-Defined Networking”, https://www.opennetworking.org/sdn-resources/sdn-definition, retrieved on May 2014.
[6] “What is MPEG DASH”, http://www.streamingmedia.com/Articles/Editorial/What-Is-.../What-is-MPEG-DASH-79041.aspx, retrieved on March 2014.
[7] Raiciu C, Pluntke C, Barre S, et al. “Data center networking with multipath TCP”, Proceedings of the 9th ACM SIGCOMM Workshop on Hot Topics in Networks. No 10, ACM, 2010.
[8] Raiciu C, Barre S, Pluntke C, et al. “Improving datacenter performance and robustness with multipath TCP”, ACM SIGCOMM Computer Communication Review. Vol. 41, no. 4, pp. 266-277.
[9] Wischik D, Raichu C, Greenhalgh A, et al. “Design, implementation and evaluation of congestion control for multipath TCP”, Proceedings of the 8th USENIX conference on Networked systems design and implementation. USENIX Association, 2011: 8-8.
[10] “Software-defined networking”, http://en.wikipedia.org/wiki/Software-defined_networking, retrieved on March 2014.
[11] “Fat Tree topology”, http://reproducingnetworkresearch.files.wordpress.com/2012/06/cs244-outcast-ft-real.jpg, retrieved on April 2014.
[12] “Fat-Tree Design”, http://clusterdesign.org/fat-trees/, retrieved on May 2014.
[13] Charles E. Leiserson, "Fat-trees: universal networks for hardware-efficient supercomputing", IEEE Transactions on Computers, Vol. 34 , no. 10, pp. 892-901, 1985.
[14] Al-Fares, Loukissas, Vahdat, "A Scalable, Commodity Data Center Network Architecture", proceedings of SIGCOMM,pp. 63-74, 2008.
[15] Nandita Dukkipati, Tiziana Refice, Yuchung Cheng, Jerry Chu, Tom Herbert, Amit Agarwal, Arvind Jain, Natalia Sutin, "TCP Increasing TCP's Initial Window", ACM SIGCOMM, Vol. 40, pp. 26-33, 2010.
[16] Blanton, Ethan, Allman, Mark, Author Paxson, "RFC 5681: TCP Congestion Control", RFC Editor, 2009.
[17] C.D. Ming, Raj Jain, "Analysis of increase and decrease algorithms for congestion avoidance in computer networks". Computer Networks and ISDN systems 17, pp. 1–14, 1989.
[18] Alex Kesselman, Yishay Mansour, "Adaptive AIMD Congestion Control", Algorithmica, Vol. 43, pp 97-111, 2005.
[19] Kirpal A. Venkatesh, Kishorekumar Neelamegam, R. Revathy, Intern, "Using MapReduce and load balancing on the cloud", IBM Technical library, 2010.
[20] Jerry Zhao, Jelena Pjesivac-Grbovic, "MapReduce: The programming model and practice", SIGMETRICS, 2009.
[21] “Mininet Overview”, “http://mininet.org/overview/”, retrieved on April 2014.
[22] “Floodlight Overview”, “http://www.projectfloodlight.org/floodlight/”, retrieved on April 2014.
[23] “DASH Support in MP4Box”, http://gpac.wp.mines-telecom.fr/mp4box/dash/, retrieved on April 2014.