Silviu S. Craciunas

Silviu S. Craciunas, Ramon Serna Oliver, Wilfried Steiner

In recent years, the IEEE 802.1 Time Sensitive Networking (TSN) task group has been active standardizing time-sensitive capabilities for Ethernet networks ranging from distributed clock synchronization and time-based ingress policing to frame preemption, redundancy management, and scheduled traffic enhancements. In particular the scheduled traffic enhancements defined in IEEE 802.1Qbv together with the clock synchronization protocol open up the possibility to schedule communication in distributed networks providing real-time guarantees. In this paper we formalize the necessary constraints for creating window-based IEEE~802.1Qbv Gate Control List schedules for Time-sensitive Networks (TSN). The resulting schedules allow a greater flexibility in terms of timing properties while still guaranteeing deterministic communication with bounded jitter and end-to-end latency.

Rubi Debnath, Daniel Bujosa Mateu, Luxi Zhao et al.

We present TSNBench, the first benchmark for evaluating large language model (LLM) proficiency in Time-Sensitive Networking (TSN), a suite of IEEE 802.1 standards for deterministic communication with bounded latency in safety-critical domains such as autonomous vehicles, aviation, defense, and industrial automation. While LLMs have been extensively evaluated on general knowledge tasks, their capabilities in safety-critical networking domains remain largely unexplored. TSNBench comprises 939 expert-validated multiple-choice questions (MCQs) covering diverse TSN mechanisms, along with 100 open-ended Worst-Case Delay (WCD) computation tasks for Credit-Based Shaper (CBS) and Cyclic Queuing and Forwarding (CQF) across varying network topologies and traffic conditions. MCQ answers are validated by domain experts, and open-ended ground truth WCD values are computed using a verified Network Calculus (NC) solver for CBS and closed-form mathematical upper bounds for CQF. We evaluate 16 LLMs and find that although models achieve 67 to 95% accuracy on MCQs, they fail substantially on open-ended WCD computation. For CBS, only GPT-5 achieves a Mean Absolute Percentage Error (MAPE) of 36.2%, meaning its predicted WCD deviates by 36.2% of the actual TSN flow delay on average, while most models exceed 80%. For CQF, the best model achieves 41.8% MAPE, with most models clustering between 80% and 100%. Such errors are large relative to TSN latency budgets and can lead to violations of real-time constraints and unsafe configurations. TSNBench demonstrates that MCQ benchmarks may overestimate LLM capabilities in safety-critical networking domains.