More Web Proxy on the site http://driver.im/

research-article

RouteNet-Fermi: Network Modeling With Graph Neural Networks

Authors:

Miquel Ferriol-Galmés,

Jordi Paillisse,

José Suárez-Varela,

Krzysztof Rusek,

Pere Barlet-Ros,

Albert Cabellos-AparicioAuthors Info & Claims

IEEE/ACM Transactions on Networking, Volume 31, Issue 6

Pages 3080 - 3095

https://doi.org/10.1109/TNET.2023.3269983

Published: 08 May 2023 Publication History

Abstract

Network models are an essential block of modern networks. For example, they are widely used in network planning and optimization. However, as networks increase in scale and complexity, some models present limitations, such as the assumption of Markovian traffic in queuing theory models, or the high computational cost of network simulators. Recent advances in machine learning, such as Graph Neural Networks (GNN), are enabling a new generation of network models that are data-driven and can learn complex non-linear behaviors. In this paper, we present RouteNet-Fermi, a custom GNN model that shares the same goals as Queuing Theory, while being considerably more accurate in the presence of realistic traffic models. The proposed model predicts accurately the delay, jitter, and packet loss of a network. We have tested RouteNet-Fermi in networks of increasing size (up to 300 nodes), including samples with mixed traffic profiles — e.g., with complex non-Markovian models — and arbitrary routing and queue scheduling configurations. Our experimental results show that RouteNet-Fermi achieves similar accuracy as computationally-expensive packet-level simulators and scales accurately to larger networks. Our model produces delay estimates with a mean relative error of 6.24% when applied to a test dataset of 1,000 samples, including network topologies one order of magnitude larger than those seen during training. Finally, we have also evaluated RouteNet-Fermi with measurements from a physical testbed and packet traces from a real-life network.

References

[1]

L. Kleinrock, “Analytic and simulation methods in computer network design,” in Proc. May Spring Joint Comput. Conf. AFIPS (Spring), 1970, pp. 569–579.

[2]

T. G. Robertazzi, Computer Networks and Systems: Queueing Theory and Performance Evaluation. Cham, Switzerland: Springer, 2000.

[3]

R. M. Fujimoto, K. Perumalla, A. Park, H. Wu, M. H. Ammar, and G. F. Riley, “Large-scale network simulation: How big? How fast?” in Proc. 11th IEEE/ACM Int. Symp. Modeling, Anal. Simulation Comput. Telecommun. Syst. (MASCOTS), Oct. 2003, pp. 116–123.

[4]

P. Almasanet al., “Digital twin network: Opportunities and challenges,” 2022, arXiv:2201.01144.

[5]

H. X. Nguyen, R. Trestian, D. To, and M. Tatipamula, “Digital twin for 5G and beyond,” IEEE Commun. Mag., vol. 59, no. 2, pp. 10–15, Feb. 2021.

[6]

S. Mirjalili, “Genetic algorithm,” in Evolutionary Algorithms and Neural Networks. Cham, Switzerland: Springer, 2019, pp. 43–55.

[7]

Z. Xuet al., “Experience-driven networking: A deep reinforcement learning based approach,” in Proc. IEEE INFOCOM Conf. Comput. Commun., Apr. 2018, pp. 1871–1879.

[8]

A. Arfeen, K. Pawlikowski, D. McNickle, and A. Willig, “The role of the Weibull distribution in modelling traffic in internet access and backbone core networks,” J. Netw. Comput. Appl., vol. 141, pp. 1–22, Sep. 2019.

[9]

T. Karagiannis, M. Molle, M. Faloutsos, and A. Broido, “A nonstationary Poisson view of internet traffic,” in Proc. IEEE INFOCOM, Mar. 2004, pp. 1558–1569.

[10]

T. Karagiannis, M. Molle, and M. Faloutsos, “Long-range dependence ten years of internet traffic modeling,” IEEE Internet Comput., vol. 8, no. 5, pp. 57–64, Sep. 2004.

[11]

E. Kresch and S. Kulkarni, “A Poisson based bursty model of internet traffic,” in Proc. IEEE 11th Int. Conf. Comput. Inf. Technol., Aug. 2011, pp. 255–260.

[12]

V. Paxson and S. Floyd, “Wide area traffic: The failure of Poisson modeling,” IEEE/ACM Trans. Netw., vol. 3, no. 3, pp. 226–244, Jun. 1995.

[13]

J. Popoola and R. Ipinyomi, “Empirical performance of Weibull self-similar tele-traffic model,” Int. J. Eng. Appl. Sci., vol. 4, no. 8, 2017, Art. no.

[14]

J. Gilmeret al., “Neural message passing for quantum chemistry,” in Proc. Int. Conf. Mach. Learn., 2017, pp. 1263–1272.

[15]

E. E. Kosasih and A. Brintrup, “A machine learning approach for predicting hidden links in supply chain with graph neural networks,” Int. J. Prod. Res., vol. 60, no. 17, pp. 5380–5393, 2021.

[16]

Q. Zhang, K. K. W. Ng, C. Kazer, S. Yan, J. Sedoc, and V. Liu, “MimicNet: Fast performance estimates for data center networks with machine learning,” in Proc. ACM SIGCOMM Conf., Aug. 2021, pp. 287–304.

[17]

Q. Yanget al., “DeepQueueNet: Towards scalable and generalized network performance estimation with packet-level visibility,” in Proc. ACM SIGCOMM Conf., Aug. 2022, pp. 441–457. 10.1145/3544216.3544248.

Digital Library

[18]

Q. Rao and J. Frtunikj, “Deep learning for self-driving cars: Chances and challenges,” in Proc. 1st Int. Workshop Softw. Eng. AI Auto. Syst., May 2018, pp. 35–38.

[19]

M. Ferriol-Galméset al. (2022). Routenet-Fermi. [Online]. Available: https://github.com/BNN-UPC/Papers/wiki/RouteNet_Fermi

[20]

J. Ma, J. Deng, and Q. Mei, “Subgroup generalization and fairness of graph neural networks,” in Proc. Adv. Neural Inf. Process. Syst., vol. 34, Dec. 2021, pp. 1048–1061.

[21]

G. Yehudai, E. Fetaya, E. Meirom, G. Chechik, and H. Maron, “From local structures to size generalization in graph neural networks,” in Proc. Int. Conf. Mach. Learn., 2021, pp. 11975–11986.

[22]

A. Al-Sawaai, I. Awan, and R. Fretwell, “Performance evaluation of weighted fair queuing system using matrix geometric method,” in Proc. Int. Conf. Res. Netw. Cham, Switzerland: Springer, 2009, pp. 66–78.

[23]

A. S. Kapadia, M. F. Kazmi, and A. C. Mitchell, “Analysis of a finite capacity non preemptive priority queue,” Comput. Oper. Res., vol. 11, no. 3, pp. 337–343, Jan. 1984.

[24]

E. Weingartner, H. vom Lehn, and K. Wehrle, “A performance comparison of recent network simulators,” in Proc. IEEE Int. Conf. Commun., Jun. 2009, pp. 1–5.

[25]

A. Varga, “Discrete event simulation system,” in Proc. Eur. Simulation Multiconference (ESM), 2001, pp. 1–7.

[26]

G. F. Riley and T. R. Henderson, “The Ns-3 network simulator,” in Modeling and Tools for Network Simulation. Cham, Switzerland: Springer, 2010, pp. 15–34.

[27]

C. R. Palmer and J. G. Steffan, “Generating network topologies that obey power laws,” in Proc. Globecom IEEE Global Telecommun. Conf. Conf. Rec., Nov. 2000, pp. 434–438.

[28]

S. K. Pal and S. Mitra, “Multilayer perceptron, fuzzy sets, and classification,” IEEE Trans. Neural Netw., vol. 3, no. 5, pp. 683–697, 1992.

[29]

N. Sadeghzadeh, A. Afshar, and M. B. Menhaj, “An MLP neural network for time delay prediction in networked control systems,” in Proc. Chin. Control Decis. Conf., Jul. 2008, pp. 5314–5318.

[30]

A. Mestres, E. Alarcón, Y. Ji, and A. Cabellos-Aparicio, “Understanding the modeling of computer network delays using neural networks,” in Proc. Workshop Big Data Anal. Mach. Learn. Data Commun. Netw., Aug. 2018, pp. 46–52.

[31]

M. Wang, Y. Cui, X. Wang, S. Xiao, and J. Jiang, “Machine learning for networking: Workflow, advances and opportunities,” IEEE Netw., vol. 32, no. 2, pp. 92–99, Mar. 2018.

[32]

T. Mikolov, S. Kombrink, L. Burget, J. Cernocky, and S. Khudanpur, “Extensions of recurrent neural network language model,” in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), May 2011, pp. 5528–5531.

[33]

S. Belhaj and M. Tagina, “Modeling and prediction of the internet end-to-end delay using recurrent neural networks,” J. Netw., vol. 4, no. 6, pp. 528–535, Aug. 2009.

[34]

A. R. Mohammed, S. A. Mohammed, and S. Shirmohammadi, “Machine learning and deep learning based traffic classification and prediction in software defined networking,” in Proc. IEEE Int. Symp. Meas. Netw. (M&N), Jul. 2019, pp. 1–6.

[35]

S. Naseeret al., “Enhanced network anomaly detection based on deep neural networks,” IEEE Access, vol. 6, pp. 48231–48246, 2018.

[36]

J. Suarez-Varelaet al., “Graph neural networks for communication networks: Context, use cases and opportunities,” IEEE Netw., early access, Aug. 1, 2022. 10.1109/MNET.123.2100773.

Digital Library

[37]

F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, “The graph neural network model,” IEEE Trans. Neural Netw., vol. 20, no. 1, pp. 61–80, Jan. 2016.

[38]

P. W. Battagliaet al., “Relational inductive biases, deep learning, and graph networks,” 2018, arXiv:1806.01261.

[39]

J. Zhouet al., “Graph neural networks: A review of methods and applications,” 2018, arXiv:1812.08434.

[40]

L. Ruiz, L. Chamon, and A. Ribeiro, “Graphon neural networks and the transferability of graph neural networks,” in Proc. Adv. Neural Inf. Process. Syst., vol. 33, 2020, pp. 1702–1712.

[41]

L. Engstromet al., “Exploring the landscape of spatial robustness,” in Proc. Int. Conf. Mach. Learn., 2019, pp. 1802–1811.

[42]

J. Su, D. V. Vargas, and K. Sakurai, “One pixel attack for fooling deep neural networks,” IEEE Trans. Evol. Comput., vol. 23, no. 5, pp. 828–841, Oct. 2019.

[43]

M. Ferriol-Galmeset al., “RouteNet-erlang: A graph neural network for network performance evaluation,” in Proc. IEEE INFOCOM Conf. Comput. Commun., May 2022, pp. 2018–2027.

[44]

K. Rusek. (2023). Queuinx. [Online]. Available: https://github.com/krzysztofrusek/queuinx

[45]

M. F.-G. Albert Lópezet al. (2023). Bnnetsimulator. [Online]. Available: https://github.com/BNN-UPC/BNNetSimulator

[46]

X. Heiet al., “Wavelength converter placement in least-load-routing-based optical networks using genetic algorithms,” J. Opt. Netw., vol. 3, no. 5, pp. 363–378, 2004.

[47]

F. Barreto, E. C. G. Wille, and L. Nacamura Jr., “Fast emergency paths schema to overcome transient link failures in OSPF routing,” 2012, arXiv:1204.2465.

[48]

J. Pedro, J. Santos, and J. Pires, “Performance evaluation of integrated OTN/DWDM networks with single-stage multiplexing of optical channel data units,” in Proc. 13th Int. Conf. Transparent Opt. Netw., Jun. 2011, pp. 1–4.

[49]

D. R. Figueiredo, B. Liu, V. Misra, and D. Towsley, “On the autocorrelation structure of TCP traffic,” Comput. Netw., vol. 40, no. 3, pp. 339–361, Oct. 2002.

[50]

S. Floyd and V. Paxson, “Difficulties in simulating the internet,” IEEE/ACM Trans. Netw., vol. 9, no. 4, pp. 392–403, Aug. 2001.

[51]

S. Knight, H. X. Nguyen, N. Falkner, R. Bowden, and M. Roughan, “The internet topology zoo,” IEEE J. Sel. Areas Commun., vol. 29, no. 9, pp. 1765–1775, Oct. 2011.

[52]

S. Orlowski, R. Wessäly, M. Pióro, and A. Tomaszewski, “SNDlib 1.0-survivable network design library,” Networks, vol. 55, no. 3, pp. 276–286, May 2010.

[53]

R. Fontugneet al., “MAWILab: Combining diverse anomaly detectors for automated anomaly labeling and performance benchmarking,” in Proc. ACM CoNEXT, Philadelphia, PA, USA, Dec. 2010, pp. 1–12.

[54]

S. Schnitter, F. Hartleb, and M. Horneffer, “Quality-of-service class specific traffic matrices in ip/mpls networks,” in Proc. 7th ACM SIGCOMM Conf. Internet Meas., Oct. 2007, pp. 253–258.

[55]

A. Valadarskyet al., “Learning to route,” in Proc. Acm Workshop Hot Topics Netw., 2017, pp. 185–191.

[56]

S. Xiao, D. He, and Z. Gong, “Deep-Q: Traffic-driven QoS inference using deep generative network,” in Proc. Workshop Netw. Meets AI ML (NetAI), 2018, pp. 67–73.

[57]

X. Chen, J. Guo, Z. Zhu, R. Proietti, A. Castro, and S. J. B. Yoo, “Deep-RMSA: A deep-reinforcement-learning routing, modulation and spectrum assignment agent for elastic optical networks,” in Proc. Opt. Fiber Commun. Conf., 2018, pp. 1–3.

[58]

F. Geyer and S. Bondorf, “DeepTMA: Predicting effective contention models for network calculus using graph neural networks,” in Proc. IEEE INFOCOM Conf. Comput. Commun., Apr. 2019, pp. 1009–1017.

[59]

K. Rusek, J. Suárez-Varela, A. Mestres, P. Barlet-Ros, and A. Cabellos-Aparicio, “Unveiling the potential of graph neural networks for network modeling and optimization in SDN,” in Proc. ACM Symp. SDN Res., Apr. 2019, pp. 140–151.

[60]

M. Wang, L. Hui, Y. Cui, R. Liang, and Z. Liu, “XNet: Improving expressiveness and granularity for network modeling with graph neural networks,” in Proc. IEEE INFOCOM Conf. Comput. Commun., May 2022, pp. 2028–2037.

[61]

J. Li, P. Sun, and Y. Hu, “Traffic modeling and optimization in datacenters with graph neural network,” Comput. Netw., vol. 181, Nov. 2020, Art. no.

Cited By

Weil JBao ZAbboud OMeuser TDastani MSichman JAlechina NDignum V(2024)Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message PassingProceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems10.5555/3635637.3663055(1919-1927)Online publication date: 6-May-2024
https://dl.acm.org/doi/10.5555/3635637.3663055
Späth JHelm MJaeger BCarle GBarlet-Ros PCasas PScarselli FSuárez-Varela JCabellos A(2024)Sim2HW: Modeling Latency Offset Between Network Simulations and Hardware MeasurementsProceedings of the 3rd GNNet Workshop on Graph Neural Networking Workshop10.1145/3694811.3697820(20-26)Online publication date: 9-Dec-2024
https://dl.acm.org/doi/10.1145/3694811.3697820
Li CNasr-Esfahany AZhao KNoorbakhsh KGoyal PAlizadeh MAnderson TSekar VYu MSeneviratne AVeitch D(2024)m3: Accurate Flow-Level Performance Estimation using Machine LearningProceedings of the ACM SIGCOMM 2024 Conference10.1145/3651890.3672243(813-827)Online publication date: 4-Aug-2024
https://dl.acm.org/doi/10.1145/3651890.3672243
Show More Cited By

Index Terms

RouteNet-Fermi: Network Modeling With Graph Neural Networks

Index terms have been assigned to the content through auto-classification.

Recommendations

Performance modeling of engine based on artificial neural networks
AICI'11: Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part III

In order to further improve the precision and generalization ability of the neural network based performance model of engine, back propagation neural network (BPNN), radial basis function neural network (RBFNN) and generalized regression neural network (...
xNet: Modeling Network Performance With Graph Neural Networks
Today’s network is notorious for its complexity and uncertainty. Network operators often rely on network models for efficient network planning, operation, and optimization. The network model is responsible for understanding the complex ...
RouteNet-Erlang: A Graph Neural Network for Network Performance Evaluation
IEEE INFOCOM 2022 - IEEE Conference on Computer Communications
Network modeling is a fundamental tool in network research, design, and operation. Arguably the most popular method for modeling is Queuing Theory (QT). Its main limitation is that it imposes strong assumptions on the packet arrival process, which ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IEEE/ACM Transactions on Networking

IEEE/ACM Transactions on Networking Volume 31, Issue 6

Dec. 2023

894 pages

ISSN:1063-6692

Issue’s Table of Contents

1558-2566 © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information.

Publisher

IEEE Press

Publication History

Published: 08 May 2023

Published in TON Volume 31, Issue 6

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
38
Total Downloads

Downloads (Last 12 months)38
Downloads (Last 6 weeks)6

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Weil JBao ZAbboud OMeuser TDastani MSichman JAlechina NDignum V(2024)Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message PassingProceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems10.5555/3635637.3663055(1919-1927)Online publication date: 6-May-2024
https://dl.acm.org/doi/10.5555/3635637.3663055
Späth JHelm MJaeger BCarle GBarlet-Ros PCasas PScarselli FSuárez-Varela JCabellos A(2024)Sim2HW: Modeling Latency Offset Between Network Simulations and Hardware MeasurementsProceedings of the 3rd GNNet Workshop on Graph Neural Networking Workshop10.1145/3694811.3697820(20-26)Online publication date: 9-Dec-2024
https://dl.acm.org/doi/10.1145/3694811.3697820
Li CNasr-Esfahany AZhao KNoorbakhsh KGoyal PAlizadeh MAnderson TSekar VYu MSeneviratne AVeitch D(2024)m3: Accurate Flow-Level Performance Estimation using Machine LearningProceedings of the ACM SIGCOMM 2024 Conference10.1145/3651890.3672243(813-827)Online publication date: 4-Aug-2024
https://dl.acm.org/doi/10.1145/3651890.3672243
Han RWang JQi QSun HXu CWan ZZhuang ZYu YLiao JTsafrir DMusuvathi MGupta RAbu-Ghazaleh N(2024)NetRen: Service Migration-Driven Network Renascence with Synthesizing Updated ConfigurationProceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 310.1145/3620666.3651365(708-721)Online publication date: 27-Apr-2024
https://dl.acm.org/doi/10.1145/3620666.3651365
Ding MGuo YHuang ZLin BLuo H(2024)GROMJournal of Network and Computer Applications10.1016/j.jnca.2024.103927229:COnline publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1016/j.jnca.2024.103927
Zheng WHong MYe RFan XLiang YZhao GZimmermann R(2023)End-to-End Delay Modeling via Leveraging Competitive Interaction Among Network FlowsIEEE Transactions on Network and Service Management10.1109/TNSM.2023.334084821:2(1634-1647)Online publication date: 8-Dec-2023
https://dl.acm.org/doi/10.1109/TNSM.2023.3340848

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Issue’s Table of Contents