Empirical Experience and Experimental Evaluation of Open5GCore over Hypervisor and Container

Hung-Cheng Chang,Bao-Shuh Paul Lin,Jyh-Cheng Chen,Bo-Jun Qiu,Tze-Jie Tan,Chen-Hao Chiu,Ping-Fan Ho

doi:10.1155/2018/6263153

Hung-Cheng Chang, Bao-Shuh Paul Lin + Show 5 more

Open Access

https://doi.org/10.1155/2018/6263153

Copy DOI

Abstract

One of the most important technologies for future 5G networks is to utilize Network Function Virtualization (NFV) to virtualize the network components. NFV provides flexibility, short time to market, and low cost solution to build network services, which are important features of 5G networks. Although the idea of virtualization is just being applied to cellular networks, it has been used in the community of cloud computing. There are two main virtualization techniques, hypervisor and container. In this paper, we present our practical experience of virtualizing Open5GCore, a commercial product of SDN-enabled Evolved Packet Core (EPC), over hypervisor and container. In addition to describing how to virtualize Open5GCore, we also present the experimental performance evaluation of the systems. Finally, some important lessons learned are provided.

Highlights

Cellular networks have been evolved to 4th generation (4G)
(iii) The installations of Open5GCore on physical machines, hypervisor, and container are tedious and sometimes troublesome if there is no script to speed up the setup process
The installations of Open5GCore on physical machines, Kernel-based Virtual Machine (KVM), and Docker are tedious and sometimes troublesome if there is no script to speed up the setup process

Summary

Introduction

One of the most important technologies for future 5G [1] networks is to utilize Network Function Virtualization (NFV) [2] to virtualize the network components in the 4G core network which is called Evolved Packet Core (EPC) [3]. NFV enables operators to virtualize hardware resources. It makes special-purpose network equipment toward software solutions, that is, Virtualized Network Function (VNF) instances. A VNF instance can run on several virtual machines (VMs) which can be scaled out/in to adjust the VNF’s computing and networking capabilities in real time. Many OSs can share the same hardware [12]. Multiple OSs can run on a single physical machine and each OS view itself owns the hardware. Virtualization techniques come with the following advantages [7, 8, 12,13,14]:

Objectives

Results

Conclusion