• DocumentCode
    3719398
  • Title

    Flow entry conflict detection scheme for software-defined network

  • Author

    Chun-Chih Lo;Pei-Yu Wu;Yau-Hwang Kuo

  • Author_Institution
    Center for Research of E-life DIgital Technology (CREDIT), Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan
  • fYear
    2015
  • Firstpage
    220
  • Lastpage
    225
  • Abstract
    Software Defined Networking (SDN) is a promising networking paradigm that decouples the network control plane from the data forwarding plane. This separation makes it possible for network administrators to overcome the complexity caused by modern networking environment. OpenFlow is a great concept to realize SDN architecture. It simplifies the network and traffic management in enterprise and data center environments by utilizing flow-based control over OpenFlow switches and providing global view of the network status. It utilizes first-matching mechanism to forward the packets in the network, and uses a prefix-based value that have binary flags in the match. However, a problem may occur when a packet matches multiple flow entries with conflicting values for the action field. By applying the first-matching mechanism to match flow entries at a switch may not always produce the desire outcome. Therefore, this paper presents a flow entry conflict detection method called Reduced Bit Vector algorithm (RBV) for SDN. RBV uses the concept of bit vectors and adopt a Group Classification method that groups the flow entries with the same prefix length together and decreases the redundant bit in vectors. The experiment result shows RBV is more efficient than other methods in terms of less search time, lower memory cost requirement, and lower incremental update time.
  • Keywords
    "Classification algorithms","Algorithm design and analysis","Control systems","Memory management","Complexity theory"
  • Publisher
    ieee
  • Conference_Titel
    Telecommunication Networks and Applications Conference (ITNAC), 2015 International
  • Type

    conf

  • DOI
    10.1109/ATNAC.2015.7366816
  • Filename
    7366816