Rongxin Han
Zirui Zhuang
ABSTRACT
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.
- Mahmoud Bahnasy, Fenglin Li, Shihan Xiao, and Xiangle Cheng. Deep-BGP: A machine learning approach for BGP configuration synthesis. In Behnaz Arzani and Xin Jin, editors, Proceedings of the 2020 Workshop on Network Meets AI & ML, Virtual Event, USA, Aug 2020.Google Scholar
Digital Library
- Shraddha Barke, Michael B. James, and Nadia Polikarpova. Grounded copilot: How programmers interact with code-generating models. Proc. ACM Program. Lang., 7(OOPSLA1):85--111, Apr 2023.Google Scholar
- Ryan Beckett, Ratul Mahajan, Todd D. Millstein, Jitendra Padhye, and David Walker. Don't mind the gap: Bridging network-wide objectives and device-level configurations. In Proceedings of the ACM SIGCOMM, Florianopolis, Brazil, Aug 2016.Google ScholarDigital Library
- Ryan Beckett, Ratul Mahajan, Todd D. Millstein, Jitendra Padhye, and David Walker. Network configuration synthesis with abstract topologies. In Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI, Barcelona, Spain, Jun 2017.Google ScholarDigital Library
- Luca Beurer-Kellner, Martin T. Vechev, Laurent Vanbever, and Petar Velickovic. Learning to configure computer networks with neural algorithmic reasoning. In NeurIPS, Louisiana, USA, Nov 2022.Google Scholar
- Matthew Caesar and Jennifer Rexford. BGP routing policies in ISP networks. IEEE Netw., 19(6):5--11, Nov-Dec 2005.Google ScholarDigital Library
- Shaowei Cai, Bohan Li, and Xindi Zhang. Local search for SMT on linear integer arithmetic. In Computer Aided Verification - 34th International Conference, CAV, Haifa, Israe, Aug 2022.Google Scholar
- Sean Choi, Boris Burkov, Alex Eckert, Tian Fang, Saman Kazemkhani, Rob Sherwood, Ying Zhang, and Hongyi Zeng. FBOSS: building switch software at scale. In Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication, SIGCOMM, Budapest, Hungary, Aug 2018.Google ScholarDigital Library
- Luca Cittadini, Stefano Vissicchio, and Giuseppe Di Battista. Doing don'ts: Modifying BGP attributes within an autonomous system. In IEEE/IFIP Network Operations and Management Symposium, NOMS, Osaka, Japan, Apr 2010.Google Scholar
- Leonardo Mendonça de Moura and Nikolaj S. Bjørner. Z3: an efficient SMT solver. In Tools and Algorithms for the Construction and Analysis of Systems, 14th International Conference, TACAS, Budapest, Hungary, Mar 2008.Google Scholar
- Ahmed El-Hassany, Petar Tsankov, Laurent Vanbever, and Martin T. Vechev. Network-wide configuration synthesis. In Computer Aided Verification - 29th International Conference, CAV, Heidelberg, Germany, Jul 2017.Google Scholar
- Ahmed El-Hassany, Petar Tsankov, Laurent Vanbever, and Martin T. Vechev. Netcomplete: Practical network-wide configuration synthesis with autocompletion. In 15th USENIX Symposium on Networked Systems Design and Implementation, NSDI, Renton, WA, USA, Apr 2018.Google Scholar
- Nick Feamster, Jay C. Borkenhagen, and Jennifer Rexford. Guidelines for interdomain traffic engineering. Comput. Commun. Rev., 33(5):19--30, Oct 2003.Google ScholarDigital Library
- Nick Feamster, Jared Winick, and Jennifer Rexford. A model of BGP routing for network engineering. In Proceedings of the International Conference on Measurements and Modeling of Computer Systems, SIGMETRICS, New York, NY, Jun 2004.Google ScholarDigital Library
- Miquel Ferriol-Galmés, Jordi Paillisse, José Suárez-Varela, Krzysztof Rusek, Shihan Xiao, Xiang Shi, Xiangle Cheng, Pere Barlet-Ros, and Albert Cabellos-Aparicio. RouteNet-Fermi: Network modeling with graph neural networks. IEEE/ACM Transactions on Networking, 31(6):3080--3095, may 2023.Google ScholarDigital Library
- Bernard Fortz and Mikkel Thorup. Internet traffic engineering by optimizing OSPF weights. In The Conference on Computer Communications, INFOCOM, Tel Aviv, Israel, Mar 2000.Google ScholarCross Ref
- Ramesh Govindan, Ina Minei, Mahesh Kallahalla, Bikash Koley, and Amin Vahdat. Evolve or die: High-availability design principles drawn from googles network infrastructure. In Proceedings of the ACM SIGCOMM 2016 Conference, Florianopolis, Brazil, Aug 2016.Google ScholarDigital Library
- Timothy G. Griffin and João L. Sobrinho. Metarouting. In Proceedings of the ACM SIGCOMM 2005 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications, Philadelphia, Pennsylvania, USA, Aug 2005.Google Scholar
- Zhou Haijun, Pan Jin, and Shen Pubing. Cost adaptive OSPF. In Proceedings Fifth International Conference on Computational Intelligence and Multimedia Applications. ICCIMA, Xi'an, China, Oct 2003.Google Scholar
- Noor Hadi Hammood, Bahaa Al-Musawi, and Ahmed Hazim Alhilali. A survey of BGP anomaly detection using machine learning techniques. In Applications and Techniques in Information Security - 12th International Conference, ATIS, Virtual Event, Dec 2021.Google Scholar
- Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun, editors, 3rd International Conference on Learning Representations, ICLR, San Diego, CA, USA, May 2015.Google Scholar
- Simon Knight, Hung X. Nguyen, Nick Falkner, Rhys Alistair Bowden, and Matthew Roughan. The internet topology zoo. IEEE J. Sel. Areas Commun., 29(9):1765--1775, Oct 2011.Google ScholarCross Ref
- Murali S. Kodialam and T. V. Lakshman. Network link weight setting: A machine learning based approach. In IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, London, United Kingdom, May 2022.Google ScholarDigital Library
- Xinjie Lin, Gang Xiong, Gaopeng Gou, Zhen Li, Junzheng Shi, and Jing Yu. ET-BERT: A contextualized datagram representation with pre-training transformers for encrypted traffic classification. In WWW '22: The ACM Web Conference 2022, Virtual Event, Lyon, France, Apr 2022.Google ScholarDigital Library
- Hongqiang Harry Liu, Xin Wu, Ming Zhang, Lihua Yuan, Roger Wattenhofer, and David A. Maltz. zUpdate: updating data center networks with zero loss. In ACM SIGCOMM 2013 Conference, Hong Kong, Aug 2013.Google ScholarDigital Library
- John Moy. OSPF version 2. RFC, 2328:1--244, 1998.Google Scholar
- Sanjai Narain, Gary Levin, Sharad Malik, and Vikram Kaul. Declarative infrastructure configuration synthesis and debugging. J. Netw. Syst. Manag., 16(3):235--258, Oct 2008.Google ScholarDigital Library
- Bruno Quoitin, Cristel Pelsser, L. Swinnen, Olivier Bonaventure, and Steve Uhlig. Interdomain traffic engineering with BGP. IEEE Commun. Mag., 41(5):122--128, May 2003.Google ScholarDigital Library
- Sivaramakrishnan Ramanathan, Ying Zhang, Mohab Gawish, Yogesh Mundada, Zhaodong Wang, Sangki Yun, Eric Lippert, Walid Taha, Minlan Yu, and Jelena Mirkovic. Practical intent-driven routing configuration synthesis. In 20th USENIX Symposium on Networked Systems Design and Implementation, NSDI, Boston, MA, Apr 2023.Google Scholar
- Yakov Rekhter, Tony Li, and Susan Hares. A border gateway protocol 4 (BGP-4). RFC, 4271:1--104, 2006.Google Scholar
- Krzysztof Rusek, José Suárez-Varela, Paul Almasan, Pere Barlet-Ros, and Albert Cabellos-Aparicio. Routenet: Leveraging graph neural networks for network modeling and optimization in SDN. IEEE J. Sel. Areas Commun., 38(10):2260--2270, Oct 2020.Google ScholarCross Ref
- Tibor Schneider, Rüdiger Birkner, and Laurent Vanbever. Snowcap: synthesizing network-wide configuration updates. In ACM SIGCOMM 2021 Conference, Virtual Event, USA, Aug 2021.Google ScholarDigital Library
- Tibor Schneider, Roland Schmid, and Laurent Vanbever. On the complexity of network-wide configuration synthesis. In 30th IEEE International Conference on Network Protocols, ICNP, Lexington, KY, USA, Oct-Nov 2022.Google ScholarCross Ref
- Shekhar Srivastava, Gaurav Agrawal, Michal Pióro, and Deep Medhi. Determining link weight system under various objectives for OSPF networks using a lagrangian relaxation-based approach. IEEE Trans. Netw. Serv. Manag., 2(1):9--18, Nov 2005.Google ScholarDigital Library
- Samuel Steffen, Timon Gehr, Petar Tsankov, Laurent Vanbever, and Martin T. Vechev. Probabilistic verification of network configurations. In SIGCOMM '20: Proceedings of the 2020 Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication, Virtual Event, USA, Aug 2020.Google Scholar
- A. Varga. Using the OMNeT++ discrete event simulation system in education. IEEE Transactions on Education, 42(4):11 pp.--, Nov 1999.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems, pages 5998--6008, Long Beach, CA, USA, Dec 2017.Google Scholar
- Stefano Vissicchio, Luca Cittadini, Laurent Vanbever, and Olivier Bonaventure. iBGP deceptions: More sessions, fewer routes. In The Conference on Computer Communications, INFOCOM, Orlando, FL, Mar 2012.Google Scholar
- Shuoyao Wang, Suzhi Bi, and Ying-Jun Angela Zhang. Deep reinforcement learning with communication transformer for adaptive live streaming in wireless edge networks. IEEE J. Sel. Areas Commun., 40(1):308--322, Jan 2022.Google ScholarDigital Library
- Zhanghao Wu, Paras Jain, Matthew A. Wright, Azalia Mirhoseini, Joseph E. Gonzalez, and Ion Stoica. Representing long-range context for graph neural networks with global attention. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, virtual, Dec 2021.Google Scholar
- Ke Xu, Hongying Liu, Jiangchuan Liu, and Meng Shen. One more weight is enough: Toward the optimal traffic engineering with OSPF. In International Conference on Distributed Computing Systems, ICDCS, Minneapolis, Minnesota, USA, Jun 2011.Google ScholarDigital Library
- Jiyun Yan, Zhenqiang Li, and Xiaohong Huang. Applications of genetic algorithms in BGP-based interdomain traffic engineering. In Communications and Networking - 11th EAI International Conference, ChinaCom, Chongqing, China, Sep 2016.Google Scholar
Index Terms
- NetRen: Service Migration-Driven Network Renascence with Synthesizing Updated Configuration
Recommendations
A cover-based approach for configuration repair
SPLC '14: Proceedings of the 18th International Software Product Line Conference - Volume 1Feature models are often used to describe variability and commonality in Software Product Lines, specifying admissible configurations of valid products. However, invalid configurations may arise in some scenarios. These include feature model evolution ...
Shadow configuration as a network management primitive
Configurations for today's IP networks are becoming increasingly complex. As a result, configuration management is becoming a major cost factor for network providers and configuration errors are becoming a major cause of network disruptions. In this ...
Shadow configuration as a network management primitive
SIGCOMM '08: Proceedings of the ACM SIGCOMM 2008 conference on Data communicationConfigurations for today's IP networks are becoming increasingly complex. As a result, configuration management is becoming a major cost factor for network providers and configuration errors are becoming a major cause of network disruptions. In this ...
Comments