An offloading scheme leveraging on neighboring node resources for edge computing over fiber-wireless (FiWi) access networks

Abstract

The computation resources at a single node in Edge Computing (EC) are commonly limited, which cannot execute large scale computation tasks. To face the challenge, an Offloading scheme leveraging on NEighboring node Resources (ONER) for EC over Fiber-Wireless (FiWi) access networks is proposed in this paper. In the ONER scheme, the FiWi network connects edge computing nodes with fiber and converges wireless and fiber connections seamlessly, so that it can support the offloading transmission with low delay and wide bandwidth. Based on the ONER scheme supported by FiWi networks, computation tasks can be offloaded to edge computing nodes in a wider range of area without increasing wireless hops (e.g., just one wireless hop), which achieves low delay. Additionally, an efficient Computation Resource Scheduling (CRS) algorithm based on the ONER scheme is also proposed to make offloading decision. The results show that more offloading requests can be satisfied and the average completion time of computation tasks decreases significantly with the ONER scheme and the CRS algorithm. Therefore, the ONER scheme and the CRS algorithm can schedule computation resources at neighboring edge computing nodes for offloading to meet the challenge of large scale computation tasks.