一句话：提出 NetRen 框架，由服务与流量迁移驱动，结合 GraphTrans 合成器与逐步修复自动生成并修复 OSPF/BGP 配置。
企业网络变更往往需要更新配置，而人工配置效率低、性能差且处理能力有限，难以保证更新后网络的可用性。本文提出 NetRen 框架，由服务与流量迁移驱动，自动合成并修复 OSPF/BGP 配置，流程包括草图提取、配置合成与配置修复。方法上先构建综合图来表示配置草图，提出基于 Transformer 的 GraphTrans 合成器，利用其长程关注与并行推理能力，并借助带优化关系的训练样本学习“按配置优化性能”的映射；随后把合成配置作为良好初始解送入逐步配置修复器，以突破可满足性瓶颈。实验显示，GraphTrans 合成器输出配置的一致性平均达 98%，NetRen 使合成效率提升 312.4 倍，网络性能提升 5.83%。
Changes in enterprise networks require updated configurations. However, manual configurations with slow update efficiency, poor performance, and handling limitations, lead to the unavailability of updated networks. Therefore, we propose an efficient network renascence framework, NetRen, which synthesizes OSPF/BGP configurations driven by service and traffic migration. We follow the workflow of sketch extraction, configuration synthesis, and repair. Initially, comprehensive graphs are constructed to represent configuration sketches. We propose a GraphTrans synthesizer with Transformer's benefits of long-range focus and parallel reasoning. Training samples with the optimization relationship enable the synthesizer to achieve a mapping that optimizes performance based on configurations. To overcome the satisfiability barrier, configurations from the synthesizer are input to the stepwise configuration repairer as well-initialized solutions, achieving rapid configuration repair. Experiments demonstrate that the consistency of network configurations output by the GraphTrans synthesizer averages 98%. NetRen achieves a 312.4× increase in synthesis efficiency and a 5.83% improvement in network performance.
@inproceedings{HanWQSXWZYL24,
title = {NetRen: Service Migration-Driven Network Renascence with Synthesizing Updated Configuration},
author = {Rongxin Han and Jingyu Wang and Qi Qi and Haifeng Sun and Chaowei Xu and Zhaoyang Wan and Zirui Zhuang and Yichuan Yu and Jianxin Liao},
booktitle = {ASPLOS},
year = {2024},
doi = {10.1145/3620666.3651365}
}