ðĪ AI Summary
In in-vehicle networks (IVNs), asynchronous traffic shapers (ATS) suffer from unbounded latency under non-FIFO behavior induced by redundancy architectures, severely compromising the determinism of time-sensitive communication. This work presents the first systematic analysis of the root cause of unbounded latency in ATS under non-FIFO redundant topologies. We propose a co-design methodology that jointly optimizes scheduler placement and configuration parameters to formally guarantee bounded end-to-end latency. Leveraging TSN-standard-compliant modeling and formal analysis of non-FIFO behaviors, we validate our approach via IVN-scale simulations on the OMNeT++/INET/TSN platform. Evaluated on realistic automotive network topologies, the method completely eliminates unbounded latency, strictly bounds maximum end-to-end latency to <100 Ξs, and achieves a 100% avoidance rate for unbounded latency instances.
ð Abstract
Time-Sensitive Networking (TSN) enhances Ethernet based In-Vehicle Networks (IVNs) with real-time capabilities. Different traffic shaping algorithms have been proposed for time-critical communication, of which the Asynchronous Traffic Shaper (ATS) is an upcoming candidate. However, recent research has shown that ATS can introduce unbounded latencies when shaping traffic from non-FIFO systems. This impacts the applicability of ATS in IVNs, as these networks often use redundancy mechanisms that can cause non-FIFO behavior. In this paper, we approach the problem of accumulated delays from ATS by analyzing the scenarios that generate latency and by devising placement and configurations of ATS schedulers to prevent this behavior. Our solution successfully mitigates problematic preconditions that lead to unbounded delays, which we evaluate in simulations. Through a realistic IVN simulation case study, we demonstrate the occurrence of unbounded latencies and validate the effectiveness of our approach in avoiding them.