Pulse+: DetNet Routing Under Delay-Diff Constraint

• Published in: IEEE Transactions on Networking pp. 1 - 15
• Main Authors: Zhao, Shizhen, Liu, Ximeng, Zhu, Tianyu, Wang, Xinbing
• Format: Journal Article
• Language: English
• Published: IEEE 10.07.2025
• Subjects: bounded jitter; Costs; delay-diff; Delays; DetNet; Jitter; Lower bound; Mission critical systems; Packet loss; Protection; Quality of service; Routing; Routing protocols
• ISSN: 2998-4157; 2998-4157
• DOI: 10.1109/TON.2025.3586040

Deterministic Networking (DetNet) is a rising technology that offers deterministic delay & jitter and extremely low packet loss in large IP networks. To achieve determinism under failure scenarios, DetNet requires finding at least two paths with close end-to-end delay, i.e., a delay-diff constraint, for mission-critical flows. However, how to find two routing paths subject to the delay-diff constraint remains open. We study the DetNet routing problem in two scenarios. First, given a primary path, we propose Pulse+, which finds a secondary path whose end-to-end delay is within a range determined by the end-to-end delay of the primary path and the delay-diff requirement. Second, we propose CoSE-Pulse+, which integrates Pulse+ with a divide-and-conquer approach to find a pair of paths that meet DetNet's delay-diff constraint. Both Pulse+ and CoSE-Pulse+ guarantee solution optimality. Notably, although Pulse+ and CoSE-Pulse+ do not have a polynomial worst-case time complexity, their empirical solver running time is better than that of other algorithms. We evaluate Pulse+ and CoSE-Pulse+ against the K-Shortest-Path and Lagrangian-dual based algorithms using synthetic test cases generated over networks with up to 10000 nodes. Both Pulse+ and CoSE-Pulse+ can solve more test cases than other algorithms under a predefined time limit. Compared to the second best algorithm, Pulse+ achieves an average-time speedup of <inline-formula> <tex-math notation="LaTeX">5\times </tex-math> </inline-formula> and CoSE-Pulse+ achieves an average-time speedup of <inline-formula> <tex-math notation="LaTeX">22\times </tex-math> </inline-formula>. Our code and test cases are available at https://gitee.com/zsz2019_shizhenzhao/drcr