Traffic Behavior in Cloud Data Centers: A Survey

TL;DR

This survey comprehensively reviews the current understanding of network traffic behavior in cloud data centers, emphasizing data collection methods, research findings, and future challenges in the field.

Contribution

It provides a systematic taxonomy and classification of recent studies on DC network traffic behavior, highlighting research gaps and future directions.

Findings

Decomposition of traffic behavior into data collection and research findings stages

Classification of recent research studies in DC traffic behavior

Identification of key research challenges in DC network traffic

Abstract

Data centers (DCs) nowadays house tens of thousands of servers and switches, interconnected by high-speed communication links. With the rapid growth of cloud DCs, in both size and number, tremendous efforts have been undertaken to efficiently design the network and manage the traffic within these DCs. However, little effort has been made toward measuring, understanding and chattelizing how the network-level traffic of these DCs behave. In this paper, we aim to present a systematic taxonomy and survey of these DC studies. Specifically, our survey first decomposes DC network traffic behavior into two main stages, namely (1) data collection methodologies and (2) research findings, and then classifies and discusses the recent research studies in each stage. Finally, the survey highlights few research challenges related to DC network traffic that require further research investigation.