A Time-Triggered Edge–Fog–Cloud Architecture With Hierarchical Genetic Optimization for Safety-Critical Applications
Josepaul Paulachan, Omar Hekal, Daniel Chidiebere Onwuchekwa, Roman Obermaisser · IEEE Access · 2025
The growth of safety-critical Internet of Things (IoT) applications, such as autonomous driving and industrial automation, demands predictable, real-time performance from distributed Edge-Fog-Cloud systems. Existing scheduling algorithms for this continuum are fundamentally unsuitable for safety-critical domains. These algorithms primarily use best-effort communication networks. This results in non-deterministic latencies and an inability to provide temporal guarantees. This paper introduces a new solution that bridges the gap between task scheduling and network determinism: a Time-Triggered Edge-Fog-Cloud (TTEFC) architecture that is based on Time-Sensitive Networking (TSN) and Deterministic Networking (DetNet) standards, ensuring bounded end-to-end communication delays; and a Hierarchical Nested Genetic Algorithm (HNGA) that effectively maps the scheduling problem onto this three-tier architecture. The HNGA consists of two genetic algorithms that use a feedback mechanism. At the top level, it is called the global genetic algorithm (GGA), which utilises graph partitioning techniques to partition the task graph into latency-aware subgraphs and assign them across the continuum. Meanwhile, nested local genetic algorithms (LGA) receive these subgraphs and perform fine-grained, time-triggered scheduling within each tier. The LGA provides the update back to the GGA, which uses the information to optimise the subgraphs such that deadlines are met and also generates the global schedule for the safety-critical applications. Experimental validation shows that this integrated approach significantly outperforms state-of-the-art scheduling methods. The proposed method was compared with the Min-Min, Particle Swarm Optimisation (PSO), and Heterogeneous Earliest Finish Time (HEFT) algorithms. The results show that the proposed method significantly reduces the makespan and consistently meets deadlines when compared to the above algorithms. Thus, the main contribution of this work is a robust and verifiable framework that provides a comprehensive solution for deploying safety-critical, real-time applications across the Edge-Fog-Cloud continuum.