A Single-Tier Fog Architecture for Delay-Sensitive and Computation-Intensive SFC Requests

Abstract

Fog computing is a promising edge network paradigm for delay-sensitive applications, attributed to the reduced link delays between nodes. However, the limited resources at the fog nodes impose restrictions to serve computation-intensive requests. Therefore, these requests are often relayed to the cloud nodes and thereby incurring link delays. This approach impedes serving requests that are both delay-sensitive and computation-intensive. Hence this paper proposes a novel single-tier fog architecture that processes this category of requests at the edge of the network. Moreover, a service function chain (SFC) provisioning scheme is implemented on the proposed architecture using Hooke Jeeves algorithm. Simulation results indicate that the proposed solution outperforms hybrid fog-cloud architectures for the same number of hosted requests (saturation level) in terms of delay and energy consumption.