English  |  正體中文  |  简体中文  |  Items with full text/Total items : 75369/75369 (100%)
Visitors : 25561623      Online Users : 315
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version

    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/71928

    Title: 基於SVM之訊務分類機制及其於SDN網路之應用;SVM-based Classification Mechanism and Its Application in SDN Networks
    Authors: 張鈺;Chang,Yu
    Contributors: 軟體工程研究所
    Keywords: 軟體定義網路;OpenFlow;網路功能虛擬化;支持向量機;訊務分類;SDN;OpenFlow;NFV;Support Vector Machine;Traffic Classification
    Date: 2016-08-29
    Issue Date: 2016-10-13 14:06:51 (UTC+8)
    Publisher: 國立中央大學
    Abstract: 近年來,由於行動寬頻、行動寬頻和物聯網的蓬勃發展,使得各式各樣的智慧型裝置普及,使用者對於網路服務即時處理能力及多樣化的服務需求也大幅提升,進而引發了更龐大更複雜的網路服務及資源使用量,加上企業面臨處理巨量資料( Big data )的需求,使得傳統網路服務的架構已無法滿足新興服務快速變動網路架構的需求。軟體定義網路( Software Defined Network, SDN )與網路功能虛擬化( Network Functions Virtualization, NFV )這兩項概念被提出,將實體複雜的網路架構轉變成虛擬、可程式化與標準化的架構,降低網路的複雜度,為傳統網路架構帶來重大的變革。而目前許多應用程式訊務封包都隱藏於超文件傳輸協定( HyperText Transfer Protocol,HTTP )與超文字傳輸安全協定( Hypertext Transfer Protocol Secure,HTTPS ),使得網路安全備受質疑。因此本論文設計基於SVM的STIC機制並應用於SDN架構,透過SDN網路集中管理與可程式化設計,分類應用程式訊務並使用VLAN技術分流網路應用程式訊務,有效減少骨幹鏈路傳輸負擔,讓網路管理者能更彈性配置網路,甚至能限制使用者可使用之應用程式,達到有效利用服務資源,減少資源浪費與配置成本,提升網路安全與服務品質。而本論文提出之STIC機制採用以特徵為基礎的預先定義分類演算法結合機器學習的支持向量機演算法,識別各種網路服務之訊務類型,包括主從式架構的Facebook、YouTube與Line等以及點對點架構的Skype、BitTorrent等等,還能透過採用決策樹方法針對特定訊務類型,進行不同層級的分類。STIC機制針對分類YouTube訊務類型有高達99%的準確率,在針對YouTube區分影音內容長度及畫質也可達到超過92%的準確度。;In recent year, as growth of the cloud computing, mobile broadband network, and Internet-of-Things technology, user requirements for network services, real-time data processing and resource management are becoming more and more diverse. The popularity of smart devices and big data is causing a considerable demand of network resources allocation and management. The Software-Defined Networking (SDN) and Network Functions Virtualization (NFV), two new network concepts have been proposed. SDN and NFV technologies are not only transforming network infrastructure from complicated physical entities to virtual and programmable nodes, but also centralizing the network control to decrease the complexity of network topology. Network security is being questioned because many application traffic hidden in the HTTP and HTTPS protocol, so SVM-based Internet Traffic Identification and Classification (STIC) are proposed to identify application traffic. STIC through the programmable nature of SDN architecture makes network easier to design, deploy, manage, reduce the waste of network resource, costs, and promote network security and quality of service. In this paper, STIC mechanism, using the signature-based scheme with the machine learning algorithms of support vector machine, is addressed to classify a variety of network service traffic such as Facebook, Line, YouTube, Skype and BitTorrent etc. STIC mechanism can not only classify about 99% YouTube traffic type but also classify over 92% about different YouTube streaming length and quality based on decision tree methods.
    Appears in Collections:[軟體工程研究所 ] 博碩士論文

    Files in This Item:

    File Description SizeFormat

    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明