Characterizing and Understanding the Architectural Implications of Cloudnative Edge NFV Workloads

Abstract

In responding to the fast-varying user service requirements and highly mixed traffics, the 5G network exploits Network Function Virtualization (NFV) and network slicing to enhance its functional and architectural viability. With the new service provisioning requirements posed by 5G (e.g. the ultra-low latency and massive machine-type communication) urge the functionality deployment to offload from the network core to edge, the various demands of QoS guarantee cast by the diverse services make the NFV an essential enabler of edge network evolution. However, the newly created performance challenges at the network edge are still unexplored. In this paper, we investigate the converged RAN and MEC architecture in the 5G era. Specifically, we characterize the collocated cloud-native workloads (RAN and MEC) on the COTS edge platform and provide the architectural implication which will benefit the future edge architecture design.