skip to main content
10.1145/3405671.3405813acmconferencesArticle/Chapter ViewAbstractPublication PagescommConference Proceedingsconference-collections
research-article

Neural Packet Routing

Published: 10 August 2020 Publication History

Abstract

Deep learning has shown great potential in automatically generating routing protocols for different optimization objectives. Although it may bring superior performance gains, there exists a fundamental obstacle to prevent existing network operators from deploying it into a real-world network, i.e., the uncertainty of statistical nature in deep learning can not provide the certainty of basic connectivity guarantee required in real-world routing.
In this paper, we propose the first deep-learning-based distributed routing system (named NGR) that can achieve the connectivity guarantee while still attaining the routing optimality. NGR provides a novel packet routing framework based on the link reversal theory. Specially-designed neural network structures are further proposed to seamlessly incorporate into the framework. We apply NGR in the tasks of shortest-path routing and load balancing. The evaluation results validate that NGR can achieve 100% connectivity guarantee despite the uncertainty of deep learning and gain performance close to the optimal solution.

References

[1]
2020. Internet Topology Zoo. http://www.topology-zoo.org/.
[2]
2020. Tensorflow. https://www.tensorflow.org/.
[3]
Justin A. Boyan and Michael L. Littman. 1993. Packet routing in dynamically changing networks: a reinforcement learning approach. In International Conference on Neural Information Processing Systems (NIPS).
[4]
Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arX-iv:1406.1078 (2014).
[5]
Samuel P. M. Choi and Dit-Yan Yeung. 1995. Predictive Q-routing: A Memory-based Reinforcement Learning Approach to Adaptive Traffic Control. In Proceedings of the 8th International Conference on Neural Information Processing Systems (NIPS).
[6]
Eli M. Gafni and Dimitri P. Bertsekas. 1981. Distributed algorithms for generating loop-free routes in networks with frequently changing topology. IEEE Transactions on Communications 29 (1981), 11--18.
[7]
Fabien Geyer and Georg Carle. 2018. Learning and generating distributed routing protocols using graph-based deep learning. In ACM SIGCOMM 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks.
[8]
Kurt Hornik, Maxwell Stinchcombe, and Halbert White. 1989. Multilayer feedforward networks are universal approximators. Neural Networks 2, 5 (1989), 359--366.
[9]
Praveen Kumar, Yang Yuan, Chris Yu, Nate Foster, Robert K-leinberg, Petr Lapukhov, Chiun Lin Lim, and Robert Soulé. 2018. Semi-Oblivious Traffic Engineering: The Road Not Taken. In NSDI 2018.
[10]
Shailesh Kumar and Risto Miikkulainen. 1998. Confidence-Based Q-Routing: An On-Line Adaptive Network Routing Algorithm. In International Joint Conference on Artificial Intelligence.
[11]
Yann Lecun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436.
[12]
Junda Liu, Aurojit Panda, Ankit Singla, Brighten Godfrey, Michael Schapira, and Scott Shenker. 2013. Ensuring connectivity via data plane mechanisms. In NSDI 2013.
[13]
Deepankar Medhi and Karthikeyan Ramasamy. 2007. Network Routing: Algorithms, Protocols, and Architectures. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.
[14]
Nithin Michael and Ao Tang. 2014. HALO: Hop-by-Hop Adaptive Link-State Optimal Routing. IEEE/ACM Transactions on Networking 23, 6 (2014), 1862--1875.
[15]
Imtiaz Parvez, Ali Rahmati, Ismail Guvenc, Arif I. Sarwat, and Huaiyu Dai. 2018. A Survey on Low Latency Towards 5G: RAN, Core Network and Caching Solutions. IEEE Communications Surveys & Tutorials (2018).
[16]
Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE Transactions on Neural Networks 20, 1 (2008), 61--80.
[17]
Tushar Swamy, Alexander Rucker, Muhammad Shahbaz, and Kunle Olukotun. 2020. Taurus: An Intelligent Data Plane. arXiv preprint arXiv:2002.08987 (2020).
[18]
Dahai Xu, Mung Chiang, and Jennifer Rexford. 2011. Link-State Routing With Hop-by-Hop Forwarding Can Achieve Optimal Traffic Engineering. IEEE/ACM Transactions on Networking 19, 6 (2011), 1717--1730.
[19]
Zhiyuan Xu, Jian Tang, Jingsong Meng, Weiyi Zhang, Yanzhi Wang, Chi Harold Liu, and Dejun Yang. 2018. Experience-driven Networking: A Deep Reinforcement Learning based Approach. In INFOCOM 2018.
[20]
Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2017. Understanding deep learning requires rethinking generalization. In ICLR 2017.

Cited By

View all
  • (2025)ScaIRComputer Networks: The International Journal of Computer and Telecommunications Networking10.1016/j.comnet.2024.110915257:COnline publication date: 1-Feb-2025
  • (2024)Graph Neural Networks for Routing Optimization: Challenges and OpportunitiesSustainability10.3390/su1621923916:21(9239)Online publication date: 24-Oct-2024
  • (2024)AdapINT: A Flexible and Adaptive In-Band Network Telemetry System Based on Deep Reinforcement LearningIEEE Transactions on Network and Service Management10.1109/TNSM.2024.342740321:5(5505-5520)Online publication date: Oct-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
NetAI '20: Proceedings of the Workshop on Network Meets AI & ML
August 2020
66 pages
ISBN:9781450380430
DOI:10.1145/3405671
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 10 August 2020

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Distributed routing
  2. deep learning
  3. reliability

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

SIGCOMM '20
Sponsor:

Acceptance Rates

Overall Acceptance Rate 13 of 38 submissions, 34%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)35
  • Downloads (Last 6 weeks)3
Reflects downloads up to 28 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)ScaIRComputer Networks: The International Journal of Computer and Telecommunications Networking10.1016/j.comnet.2024.110915257:COnline publication date: 1-Feb-2025
  • (2024)Graph Neural Networks for Routing Optimization: Challenges and OpportunitiesSustainability10.3390/su1621923916:21(9239)Online publication date: 24-Oct-2024
  • (2024)AdapINT: A Flexible and Adaptive In-Band Network Telemetry System Based on Deep Reinforcement LearningIEEE Transactions on Network and Service Management10.1109/TNSM.2024.342740321:5(5505-5520)Online publication date: Oct-2024
  • (2024)DAR-DRL: A Dynamic Adaptive Routing Method based on Deep Reinforcement LearningComputer Communications10.1016/j.comcom.2024.107983(107983)Online publication date: Oct-2024
  • (2023)Reliable PPO-Based Concurrent Multipath Transfer for Time-Sensitive ApplicationsIEEE Transactions on Vehicular Technology10.1109/TVT.2023.327771272:10(13575-13590)Online publication date: Oct-2023
  • (2023)Mistill: Distilling Distributed Network Protocols From ExamplesIEEE Transactions on Network and Service Management10.1109/TNSM.2023.326352920:4(4110-4125)Online publication date: Dec-2023
  • (2022)Taurus: a data plane architecture for per-packet MLProceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems10.1145/3503222.3507726(1099-1114)Online publication date: 28-Feb-2022
  • (2022)PPO-based Reliable Concurrent Transmission Control for Telemedicine Real-time ServicesICC 2022 - IEEE International Conference on Communications10.1109/ICC45855.2022.9839084(4655-4660)Online publication date: 16-May-2022
  • (2022)Near-optimal responsive traffic engineering in software defined networks based on deep learningFuture Generation Computer Systems10.1016/j.future.2022.04.036135:C(172-180)Online publication date: 1-Oct-2022
  • (2022)Graph-based deep learning for communication networksComputer Communications10.1016/j.comcom.2021.12.015185:C(40-54)Online publication date: 1-Mar-2022
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media