Beyond Dedicated-Active: A General Reliability Provisioning Framework for SFC Placement in Fog Computing

TL;DR

This paper proposes a reliability-aware framework for Service Function Chain placement in fog computing, optimizing latency, cost, and reliability using genetic algorithms, with shared-standby redundancy significantly outperforming traditional methods.

Contribution

It introduces a general framework for reliability-aware SFC placement in heterogeneous fog environments, incorporating novel redundancy strategies and optimization algorithms.

Findings

Shared-standby redundancy reduces failure rates by up to 84%.

The proposed genetic algorithms effectively optimize latency and cost.

Reliability constraints are successfully integrated into the placement problem.

Abstract

The explosive growth of Internet of Things (IoT) devices has strained traditional cloud infrastructures, highlighting the need for low-latency and energy-efficient alternatives. Fog computing addresses this by placing computation near the network edge. However, limited and heterogeneous fog resources pose reliability challenges, especially for mission-critical applications. On the other hand, to improve flexibility, applications are deployed as Service Function Chains (SFCs), where each function runs as a Virtual Network Function (VNF). While scalable, this approach is more failure-prone than monolithic deployments, necessitating intelligent redundancy and placement strategies. This paper addresses the reliability-aware SFC placement problem over heterogeneous fog servers through the lens of reliability theory. We explore four redundancy strategies, combining shared vs. dedicated and active vs. standby modes, and propose a general framework to minimize latency and cost while meeting reliability and deadline constraints. The problem is formulated as an Integer Non-Linear Program (INLP), and two genetic algorithm (GA)-based solutions are developed. Simulation results show that shared-standby redundancy outperforms the conventional dedicated-active approach by up to 84%.