Recently, edge computing has emerged as a promising computing paradigm  to meet stringent quality-of-service requirements of an increasing  number of latency-sensitive applications. The core principle of edge  computing is to bring the capability of cloud computing in close  proximity to mobile devices, sensors, actuators, connected things and  end users, thereby supporting various types of services and applications  at the network edge. In this article, we design capacity-centric FiWi  broadband access networks enhanced with edge computing as well as  resulting fiber backhaul sharing and computation offloading  capabilities. More specifically, we introduce the concept of FiWi  enhanced two-level edge computing at the access edge cloud and metro  edge cloud. To guarantee low end-to-end latency, we propose a TDMA based  polling scheme for resource management. Furthermore, given the vital  importance of experimentally demonstrating the potential and practical  limitations of edge computing, we develop an experimental testbed for  edge computing across converged FiWi broadband access networks. The  proof-of-concept demonstration of the testbed is studied in terms of  response time and response time efficiency of both edge clouds,  including their respective energy consumption.

Rimal, B.P., Maier, M., Satyanarayanan, M.
IEEE Communications Magazine, 56(160-167), August 2018