TY - GEN
T1 - Fault Tolerant Controller Placement in Distributed SDN Environments
AU - Alshamrani, Adel
AU - Guha, Sayantan
AU - Pisharody, Sandeep
AU - Chowdhary, Ankur
AU - Huang, Dijiang
N1 - Funding Information:
This research is based upon work supported by the NSF under Grants 1642031 and 1528099, and NSFC under Grants 61628201 and 61571375.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/27
Y1 - 2018/7/27
N2 - Software Defined Network (SDN) facilitates a centralized networking system where a controller manages the global view of the network. The introduction of Software-Defined Networks and standards such as OpenFlow spawn several questions regarding scalability and reliability. One such question is the controller placement problem; i.e. given a topology, the problem of determining how many controllers are needed, and where they should be placed. This question has been well-studied relative to performance, but there has not been a focus on maximizing fault-tolerance. In this paper, we present a model for controller placement to account for fault-tolerance and compare our algorithm to existing algorithms. Our proposed solution was analyzed to determine where controllers should be placed on a wide range of topologies from the Internet Topology Zoo. We further evaluated the dependence of fault-tolerance over the range of available number of controllers.
AB - Software Defined Network (SDN) facilitates a centralized networking system where a controller manages the global view of the network. The introduction of Software-Defined Networks and standards such as OpenFlow spawn several questions regarding scalability and reliability. One such question is the controller placement problem; i.e. given a topology, the problem of determining how many controllers are needed, and where they should be placed. This question has been well-studied relative to performance, but there has not been a focus on maximizing fault-tolerance. In this paper, we present a model for controller placement to account for fault-tolerance and compare our algorithm to existing algorithms. Our proposed solution was analyzed to determine where controllers should be placed on a wide range of topologies from the Internet Topology Zoo. We further evaluated the dependence of fault-tolerance over the range of available number of controllers.
KW - Controller
KW - Controller placement
KW - Fault Tolerance (FT)
KW - Metric
KW - OpenFlow
KW - Software-Defined Network (SDN)
UR - http://www.scopus.com/inward/record.url?scp=85051417968&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051417968&partnerID=8YFLogxK
U2 - 10.1109/ICC.2018.8422593
DO - 10.1109/ICC.2018.8422593
M3 - Conference contribution
AN - SCOPUS:85051417968
SN - 9781538631805
T3 - IEEE International Conference on Communications
BT - 2018 IEEE International Conference on Communications, ICC 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Communications, ICC 2018
Y2 - 20 May 2018 through 24 May 2018
ER -