Journal of Communications and Information Networks
Vol.2, No.3, Sept. 2017
DOI: 10.1007/s41650-017-0030-x
Research paper
The controller placement problem or
the controller selection problem?
Keshav Sood, Yong Xiang
School of Information Technology, Deakin University, Melbourne 3215, Australia
Abstract: In SDN, the control logic of packet processing devices is moved onto the SDN centralized
controller. This decoupled networking architecture creates some critical concerns when compared to
traditional distributed architectures. One primary concern in this architecture is the placement of the
controller, which is commonly known as the CPP. From our extensive literature review, we identify that
there is no strict placement rule that best fits every network in SDN. Dynamic addition and deletion of
controllers is inevitable. Motivated from this, in this paper, we attempt to transform the CPP into a CSP.
We show that, in the dynamic SDN environment, researchers need to pay attention to CSP issues. The clear
advantage of CSP over CPP is that, in the dynamic SDN ecosystem, we can answer fundamental questions
about the control plane performance, i.e., minimum number of controllers, their workload distribution, and
placement/locations. Furthermore, we can meet strict, application-specific, QoS constraints.
Keywords: software-defined network, controller placement problem, flow balancing in SDN, quality of ser-
vice, distributed networks, future networks
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Citation: K. Sood, Y. Xiang. The controller placement problem or the controller selection problem? [J].
Journal of communications and information networks, 2017, 2(3): 1-9.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
1 Introduction
Traditional computer networks do not scale well and
are inadequate to fulfill the needs and requirements
of the current Internet environment. In order to ad-
dress this, SDN (Software-Defined Network), which
represents a transformation from traditional switch-
ing to a new programmable switching technology,
was proposed. SDN is considered as a tectonic
shift in the networking industry and the anticipation
come a degree of over-hype. The concept of SDN is
substantially different from that of the traditional
switching architectures.
In SDN principles, the control logic of data plane
elements, such as switches and routers, etc. is shifted
onto the control plane elements, like physical and
logical SDN controllers
[1]
. This simplifies the man-
agement of complex networks and brings about many
other significant advantages. However, this decou-
pling of planes adversely affects the control plane
performance, and their associated issues such as la-
tency, scalability, and availability (of the decoupled
SDN architectures) are largely unstudied
[2]
. This de-
coupled and centralized architecture almost affects
almost every aspect of network performance. The
switch-controller distance imposed fundamental lim-
itations on the controller availability and response
time or flow-setup time for flows/packets, especially
in WANs
[3]
. Owing to the limited capacity of han-
dling flows by software-based controllers for handling
flows, it is very challenging to respond to events in
real-time, or it is difficult for controllers to behave
Manuscript received Jun. 12, 2017; accepted Jul. 19, 2017