Exploring the Impact of Critical Programmability on Controller Placement for Software-Defined Wide Area Networks

Control latency is a critical concern for deploying Software-Defined Networking (SDN) into Wide Area Networks (WANs). A Software-Defined WAN (SD-WAN) can be divided into multiple domains controlled by multiple controllers with a logically centralized view. The control latency is related to the placement of controllers and mappings between switches and controllers. Existing solutions usually consider the propagation delay between switches and controllers as the evaluation metric and fail to consider many important factors of dynamic network states. In this paper, we propose ProgrammabilityExplorer (PE) to optimize the control latency in SD-WAN. Inspired by the selection of critical flows, which have a critical impact on network performance, PE considers the programmability of critical flows at switches and uses this metric to decide the placement of controllers and mappings between switches and controllers. Simulation results show that PE can reduce the control latency by up to 62.3%, 27.5%, 58.3%, and 61.7% under GÉANT, Abilene, Sprintlink, and Tiscali topologies respectively, compared with baseline algorithms.

I. Introduction

Wide Area Networks (WANs) are of great significance in the real world. It connects different types of networks (e.g., data center networks, cellular networks, and metropolitan area networks) and transfers traffic among these networks to provide network applications. The emerging Software-Defined Networking (SDN) promises significant improvement in the performance of WANs with logically centralized control. Typically, a Software-Defined WAN (SD-WAN) is of large scale and is usually composed of multiple domains, each of which consists of one SDN controller to control flows traversing SDN switches placed in its domain. SDN controllers synchronize with each other to maintain a global network view [2].