Abstract:
The integration of control and data planes into the same devices and lack the
global centralization control that made the traditional networks may not meet the
requirements of the emerging cloud computing, the tactile Internet, and the Internet of
Things (IoT) technology. Moreover, the traditional networks cannot provide the
complexity of control protocols, complex traffic engineering (TE) tasks, and
interconnecting of a huge number of smart devices. Software Defined Networking
(SDN) is an architecture that overcomes the above issues of the traditional networks by
taking advantage of global centralization control, decouples of the control and data
planes, and enabling innovation through the network programmability.
The shortest path-based routing cannot guarantee future traffic demands
because the routing only uses the minimum hop counts. The application-aware routing
is more efficient than the traditional shortest path-based routing; however, classification
of application traffic and estimation of QoS parameters like link utilization and link
delay are needed to perform such kind of routing. By taking the advantage of SDN,
application-aware traffic engineering can perform more effectively in SDN
environments.
This dissertation presents an application-aware traffic engineering (App-TE) in
SDN which generally involves three main modules: traffic classification, traffic
measurement, and traffic management. Application traffic flows classified into the
following two classes: prioritized application traffic and non-prioritized application
traffic by using port number and protocol number with the help of traffic analyzer
(sFlow-RT). The classified traffic flows are fed to the traffic measurement module to
calculate the link utilization, link delay, and Delay Weighted Capacity (DWC) values.
Finally, prioritized application traffic flows are routed by using the DWC-aware routing
and non-prioritized application traffic flows are routed by using shortest path routing
(or) minimum hop-count based routing. The experimental results demonstrated that the
average throughput results of the proposed App-TE outperformed the shortest path
routing and LU-aware routing.
