ReWeave: Traffic Engineering with Robust Path Weaving for Localized Link Failure Recover

2025-08-31

AI Summary

To address the insufficient robustness and scalability of traffic engineering (TE) in ISP networks caused by frequent link failures, this paper proposes a low-overhead, highly scalable local rerouting mechanism. The core innovation lies in designing compact SRv6 backup paths for each link—computed solely from adjacency information of neighboring nodes—enabling autonomous, distributed rerouting upon failure without centralized controller involvement or global path recomputation. By integrating link-level TE with source-routed fast forwarding, the scheme achieves rapid, localized failure recovery. Evaluation on large-scale backbone networks shows that, compared to HARP, it reduces maximum link utilization by 10.5%–20.1% under typical conditions and by 29.5%–40.9% in worst-case scenarios. In 90% of failure cases, packet loss matches that of Flexile, while response latency approaches that of optimal local rerouting schemes.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Local Search
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Large-scale security measurements

Abstract

Link failures occur frequently in Internet Service Provider (ISP) networks and pose significant challenges for Traffic Engineering (TE). Existing TE schemes either reroute traffic over vulnerable static paths, leading to performance degradation, or precompute backup routes for a broad range of failure scenarios, which introduces high overhead and limits scalability. Hence, an effective failure recovery mechanism is required to offer sufficient path diversity under constrained overhead, thereby ensuring robust and performant network operation. This paper presents ReWeave, a scalable and efficient link-level TE scheme that enables localized rerouting by equipping each link with a compact set of adjacent-only backup paths. Upon detecting a failure, only the routers at both ends of the failed link reroute traffic dynamically using SRv6-based detours, without controller intervention or full-path recomputation. Evaluation results on large-scale backbone networks demonstrate that ReWeave outperforms existing TE schemes in link failure scenarios. Compared to HARP, the state-of-the-art failure recovery scheme based on centralized control and dynamic traffic reallocation, our approach reduces the average maximum link utilization by 10.5%~20.1%, and lowers the worst-case utilization by 29.5%~40.9%. When compared with Flexile, a protection-based scheme that precomputes routes for multi-failure scenarios, ReWeave achieves a similarly low packet loss rate in 90% of failure cases, while maintaining a response speed comparable to the fastest router-based local rerouting schemes.

Problem

• Robust traffic engineering for localized link failure recovery
• Scalable backup path solution minimizing network overhead
• Dynamic rerouting without controller intervention using SRv6

Innovation

• Localized rerouting with adjacent-only backup paths
• SRv6-based detours without controller intervention
• Compact path sets for scalable failure recovery