Control plane latency reduction for service chaining in mobile edge computing system

Abstract

Software-Defined Networking and Network Function Virtualization technologies are utilized to construct service chains cheaply and elastically. In Mobile Edge Computing platform, cloud servers can be deployed near to base stations. Migrating service functions of service chains to edge can reduce network latency or save unnecessary bandwidth consumption between edge and cloud datacenter. However, the control plane latency of SDN/NFV Mobile Edge Computing Platform is subject to the scalability of flow table in SDN switches due to flow table overflow problem. In this paper, we proposed Hash-based Group Management scheme to reduce the number of maintained flow entries by assigning users into groups and design a hash-based structure to efficiently maintain the group information. In our simulation results, the proposed scheme can reduce the number of maintain flow entries and table overflow ratio to improve the control plane latency.