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%.

翻译：物联网设备的爆炸式增长对传统云基础设施造成了压力，凸显了对低延迟和节能替代方案的需求。雾计算通过将计算资源部署在网络边缘附近来解决这一问题。然而，有限且异构的雾资源带来了可靠性挑战，特别是对于关键任务应用。另一方面，为了提高灵活性，应用通常以服务功能链的形式部署，其中每个功能作为虚拟网络功能运行。虽然这种方法具有可扩展性，但与单体式部署相比更易发生故障，因此需要智能的冗余和部署策略。本文从可靠性理论的角度，研究了异构雾服务器上考虑可靠性的服务功能链部署问题。我们探讨了四种冗余策略，结合了共享与专用、主动与备用模式，并提出了一个通用框架，以在满足可靠性和截止时间约束的同时，最小化延迟和成本。该问题被建模为一个整数非线性规划问题，并开发了两种基于遗传算法的解决方案。仿真结果表明，共享-备用冗余策略相比传统的专用-主动方法，性能提升高达84%。