Toward Adaptive and Scalable OpenFlow-SDN Flow Control: A Survey

Mohammed Alsaeedi,Anas A Al-Roubaiey,Mohd Murtadha Mohamad

doi:10.1109/access.2019.2932422

Abstract

Software-defined networking (SDN) is an emerging network architecture that promises to simplify network management, improve network resource utilization, and boost evolution and innovation in traditional networks. The SDN allows the abstraction and centralized management of the lower-level network functionalities by decoupling the network logic from the data forwarding devices into the logically centralized distributed controllers. However, this separation introduces new scalability and performance challenges in large-scale networks of dynamic traffic and topology conditions. Many research studies have represented that centralization and maintaining the global network visibility over the distributed SDN controller introduce scalability concern. This paper surveys the state-of-the-art proposed techniques toward minimizing the control to data planes communication overhead and controllers' consistency traffic to enhance the OpenFlow-SDN scalability in the context of logically centralized distributed SDN control plane architecture. The survey mainly focuses on four issues, including logically centralized visibility, link-state discovery, flow rules placement, and controllers' load balancing. In addition, this paper discusses each issue and presents an updated and detailed study of existing solutions and limitations in enhancing the OpenFlow-SDN scalability and performance. Moreover, it outlines the potential challenges that need to be addressed further in obtaining adaptive and scalable OpenFlow-SDN flow control.

Highlights

Today’s Internet is used as a global communication platform for the heterogeneous and large number of dynamic applications, services, physical objects, and machines
According to the Enterprise Strategy Group (ESG), traditional networks require to automate the manual processes of network management, provides better visibility for efficient resource utilization and provides dynamic network orchestration to align with cloud computing
We focus on the state-of-the-art proposed mechanisms toward reducing the traffic overhead between control and data planes caused by the reactive flow-rules placement, and classify them into five schemes: Control back to data plane, flow table entries reduction, per-flow source routing, adaptive flow entry’s timeout and predictive flow rules placement

Summary

Introduction

Today’s Internet is used as a global communication platform for the heterogeneous and large number of dynamic applications, services, physical objects, and machines. Network traffic control and orchestration in modern networks is a very complex task that requires to adapt to the time-varying changes in link utilization, bandwidth allocation, latency, energy consumption, and jitter over a heterogeneous network. The emerging Internet of Things (IoT) and the adoption of multi-tenant data centers (DC) generate a large amount of traffic and add more complexity to the network. The compact integration of control and data planes complicates the network traffic monitoring process resulted in less QoS-aware flow control. It is time-consuming and expensive to manage the network devices separately especially in time-varying and multi-tenant data center environments. According to the Enterprise Strategy Group (ESG), traditional networks require to automate the manual processes of network management, provides better visibility for efficient resource utilization and provides dynamic network orchestration to align with cloud computing. ESG stats that as data center grows in scale, network management operators struggle of too many manual and reconfiguration processes, which may reach nearly 40 percent of the most common network operations problems

Objectives

Findings

Conclusion