Multicast-partitioning in Time-triggered Stream Planning for Time-Sensitive Networks

TL;DR

This work tackles the challenge of schedulability in Time-Sensitive Networking (TSN) when using multicast by introducing multicast partitioning to split large multicast trees into smaller, more schedulable units. The approach creates partitions based on a hop-distance threshold, enabling a trade-off between bandwidth efficiency and scheduling complexity, and is applied as a preprocessing step before TSN scheduling. Evaluations across diverse topologies and three scheduling algorithms show that partitioning reduces stream rejections and increases accumulated network throughput, with gains varying by topology and scheduler (e.g., up to 125% throughput improvement with Greedy and up to 5% with GFH). The findings demonstrate that tree partitioning is a robust, topology-dependent method to improve real-time network performance, while future work should focus on dynamic threshold adaptation to active network conditions.

Abstract

Multicast allows sending a message to multiple recipients without having to create and send a separate message for each recipient. This preserves network bandwidth, which is particularly important in time-sensitive networks. These networks are commonly used to provide latency-bounded communication for real-time systems in domains like automotive, avionics, industrial internet of things, automated shop floors, and smart energy grids. The preserved bandwidth can be used to admit additional real-time messages with specific quality of service requirements or to reduce the end-to-end latencies for messages of any type. However, using multicast communication can complicate traffic planning, as it requires free queues or available downstream egress ports on all branches of the multicast tree. In this work, we present a novel multicast partitioning technique to split multicast trees into smaller multicast or unicast trees. This allows for a more fine-grained trade-off between bandwidth utilization and traffic scheduling difficulty. Thus, schedulability in dynamic systems can be improved, in terms the number of admitted streams and the accumulated network throughput. We evaluated the multicast partitioning on different network topologies and with three different scheduling algorithms. With the partitioning, 5-15\% fewer streams were rejected, while achieving 5-125\% more network throughput, depending on the scheduling algorithm.

Figures (5)

• Figure 1: Two-phase process of multicast partitioning and scheduling. $\mathcal{S}$ denotes a set of streams: to be added ($\mathcal{S}_i^\text{add}$) to the system, removed ($\mathcal{S}_i^\text{del}$) from the system, that were rejected ($\mathcal{S}_i^\text{rej}$), or the admitted streams before ($\mathcal{S}_i$) and after ($\mathcal{S}_{i+1}$) the scheduling update.
• Figure 2: Comparison of multicast partitioning versus non-partitioning on different network topologies.
• Figure 3: Evaluation of GFH and Greedy heuristics on random networks with 49 bridges after either performing or not performing multicast partitioning. The number after the scheduler name denotes the partitioning threshold.
• Figure 4: Cumulative rejected streams using a no-wait constraint programming scheduler with a scheduling time limit of 60s.
• Figure 5: Difference in cumulative rejected streams. Negative values imply that the GFH scheduling with the given partitioning threshold rejected fewer streams than GFH scheduling without partitioning.