Abstract Industrial Internet of Things (IIoT) provide a promising opportunity for building efficient industrial wireless systems by leveraging the growing ubiquity of sensor nodes. However, IIoT exhibits strict reliability and has a high requirement for real-time communications. Furthermore, different criticality level flows are coexisted in many IIoT. The system must guarantee the reliability and real-time performance of high-criticality flows to avoid disasters. To address this issue, this paper first proposes a heterogeneous routing model in which both source and graph routing coexist. Then, we propose Relative-execution Deadline First (RDF) scheduling and prove it has a better performance than the fixed priority (FP) and earliest deadline first (EDF) methods. By extending RDF in mixed-criticality IIoT, a Mixed-Criticality Relative-execution Deadline scheduling algorithm (MCRD) has proposed, which can further improve system schedulability by making a trade-off between reliability and real-time performance. Simulation and experiment results show that our approach outperforms the existing methods.

中文翻译：

---

工业物联网异构路由下的实时调度

摘要 工业物联网 (IIoT) 为利用日益普遍的传感器节点构建高效的工业无线系统提供了一个有希望的机会。然而，IIoT 表现出严格的可靠性，并且对实时通信有很高的要求。此外，在许多 IIoT 中，不同的临界级别流共存。系统必须保证高危流的可靠性和实时性才能避免灾难。为了解决这个问题，本文首先提出了一种源路由和图路由共存的异构路由模型。然后，我们提出了相对执行期限优先（RDF）调度，并证明它比固定优先级（FP）和最早期限优先（EDF）方法具有更好的性能。通过在混合关键 IIoT 中扩展 RDF，提出了一种混合临界相对执行期限调度算法（MCRD），通过在可靠性和实时性之间进行权衡，可以进一步提高系统的可调度性。仿真和实验结果表明，我们的方法优于现有方法。