4.6 Article

AVB-Aware Routing and Scheduling of Time-Triggered Traffic for TSN

Journal

IEEE ACCESS
Volume 6, Issue -, Pages 75229-75243

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2018.2883644

Keywords

IEEE 802.1 Time-sensitive networking; deterministic ethernet; real-time networks; routing; scheduling; meta-heuristic optimization

Funding

  1. ENABLE-S3 Project from the ECSEL Joint Undertaking [692455]

Ask authors/readers for more resources

IEEE 802.1 time-sensitive networking (TSN) is a set of amendments to the IEEE 802.1 standard that enable safety-critical and real-time behavior over Ethernet for the industrial automation and automotive domains. Selected TSN mechanisms offer the possibility to emulate the well-known traffic classes found in mixed-criticality distributed systems: Time-triggered (TT) communication with low jitter and bounded end-to-end latency, audio-video-bridging (AVB) streams with bounded end-to-end latency, and general best-effort messages, which have no timing guarantees. Critical traffic is guaranteed via the global network schedule which is stored in so-called gate control lists (GCLs) and controls the timely behavior of frames for each queue of an egress port. Although researchers have started to propose approaches for the routing and scheduling (i.e., GCL synthesis) of TT traffic, all previous research has ignored lower priority real-time traffic, such as AVB, resulting in TT configurations that may increase the worst-case delays of AVB traffic, rendering it unschedulable. In this paper, we propose a joint routing and scheduling approach for TT traffic, which takes into account the AVB traffic, such that both TT and the AVB traffic are schedulable. We extensively evaluate our approach on a number of synthetic and realistic test cases.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available