Cost-Efficient Dynamic Service Function Chain Embedding in Edge Clouds

Abstract

Edge Computing (EC) provides delay protection for some delay-sensitive network services by deploying cloud infrastructure with limited resources at the edge of the network. In addition, Network Function Virtualization (NFV) implements network functions by replacing traditional dedicated hardware devices with Virtual Network Function (VNF) that can run on general servers. In NFV environment, Service Function Chaining (SFC) is regarded as a promising way to reduce the cost of configuring network services. NFV therefore allows to deploy network functions in a more flexible and cost-efficient manner, and schedule network resources according to the dynamical variation of network traffic in EC. For service providers, seeking an optimal SFC embedding scheme can improve service performance and reduce embedding cost. In this paper, we study the problem of how to dynamically embed SFC in geo-distributed edge clouds network to serve user requests with different delay requirements, and formulate this problem as a Mixed Integer Linear Programming (MILP) which aims to minimize the total embedding cost. Furthermore, a novel SFC Cost-Efficient emBedding (SFC-CEB) algorithm has been proposed to efficiently embed required SFC and optimize the embedding cost. Based on the results of trace-driven simulations, the proposed algorithm can reduce SFC embedding cost by up to 37% compared with state-of-the-art schemes (e.g., RDIP).