Routing and Scheduling for Low Latency and Reliability in Time-Sensitive Software-Defined IIoT

Time-sensitive software-defined networking (TSSDN) is an emerging technology that combines the real-time network configuration capabilities of software-defined networking (SDN) with the deterministic flow delivery capabilities of time-sensitive networking (TSN), making it ideal for use in the Industrial Internet of Things (IIoT). However, as data flows generated by industrial applications grow exponentially, it is challenging to achieve low-latency and reliable data flow transmission at the same time in TSSDN due to the limited network resources. To address this issue, we propose the adoption of the frame replication and elimination for reliability (FRER) mechanism in TSSDN-based IIoT systems. However, it is important to acknowledge that the FRER mechanism introduces stress on the already restricted network resources by generating redundant paths. In light of this concern, we construct an end-to-end delay bound model and a reliability model to analyze this issue. To mitigate the stress imposed on the network, we formulate an optimization problem for maximizing the overall system utility while adhering to the transmission requirements of business flows and the limitations of hardware resources. Consequently, we devise an algorithm for reliability-enhanced flow routing and scheduling, which effectively solves the aforementioned optimization problem. To validate the effectiveness and performance of our proposed algorithm, we conduct numerical simulations on four data sets. The results demonstrate the superior performance of our approach compared to existing methods.