RouteNet-Fermi: Network Modeling with Graph Neural Networks

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 loss in networks. 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 it is able to accurately scale to large networks. For example, the model produces delay estimates with a mean relative error of 6.24% when applied to a test dataset with 1,000 samples, including network topologies one order of magnitude larger than those seen during training.

[1]  Zhen Liu,et al.  xNet: Improving Expressiveness and Granularity for Network Modeling with Graph Neural Networks , 2022, IEEE INFOCOM 2022 - IEEE Conference on Computer Communications.

[2]  Miquel Ferriol Galmés,et al.  RouteNet-Erlang: A Graph Neural Network for Network Performance Evaluation , 2022, IEEE INFOCOM 2022 - IEEE Conference on Computer Communications.

[3]  Diego Perino,et al.  Digital Twin Network: Opportunities and Challenges , 2022, ArXiv.

[4]  Miquel Ferriol Galmés,et al.  Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities , 2021, IEEE Network.

[5]  Vincent Liu,et al.  MimicNet: fast performance estimates for data center networks with machine learning , 2021, SIGCOMM.

[6]  Alexandra Brintrup,et al.  A machine learning approach for predicting hidden links in supply chain with graph neural networks , 2021, Int. J. Prod. Res..

[7]  Mallik Tatipamula,et al.  Digital Twin for 5G and Beyond , 2021, IEEE Communications Magazine.

[8]  Yuxiang Hu,et al.  Traffic modeling and optimization in datacenters with graph neural network , 2020, Comput. Networks.

[9]  Muhammad Asad Arfeen,et al.  The role of the Weibull distribution in modelling traffic in Internet access and backbone core networks , 2019, J. Netw. Comput. Appl..

[10]  Shervin Shirmohammadi,et al.  Machine Learning and Deep Learning Based Traffic Classification and Prediction in Software Defined Networking , 2019, 2019 IEEE International Symposium on Measurements & Networking (M&N).

[11]  Fabien Geyer,et al.  DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks , 2019, IEEE INFOCOM 2019 - IEEE Conference on Computer Communications.

[12]  Albert Cabellos-Aparicio,et al.  Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN , 2019, SOSR.

[13]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[14]  Muhammad Munwar Iqbal,et al.  Enhanced Network Anomaly Detection Based on Deep Neural Networks , 2018, IEEE Access.

[15]  Zhibo Gong,et al.  Deep-Q: Traffic-driven QoS Inference using Deep Generative Network , 2018, NetAI@SIGCOMM.

[16]  Yusheng Ji,et al.  Understanding the Modeling of Computer Network Delays using Neural Networks , 2018, Big-DAMA@SIGCOMM.

[17]  Razvan Pascanu,et al.  Relational inductive biases, deep learning, and graph networks , 2018, ArXiv.

[18]  Roberto Proietti,et al.  Deep-RMSA: A Deep-Reinforcement-Learning Routing, Modulation and Spectrum Assignment Agent for Elastic Optical Networks , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[19]  Chi Harold Liu,et al.  Experience-driven Networking: A Deep Reinforcement Learning based Approach , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[20]  Aleksander Madry,et al.  Exploring the Landscape of Spatial Robustness , 2017, ICML.

[21]  Dafna Shahaf,et al.  Learning to Route , 2017, HotNets.

[22]  Kouichi Sakurai,et al.  One Pixel Attack for Fooling Deep Neural Networks , 2017, IEEE Transactions on Evolutionary Computation.

[23]  Xin Wang,et al.  Machine Learning for Networking: Workflow, Advances and Opportunities , 2017, IEEE Network.

[24]  R. A. Ipinyomi,et al.  Empirical Performance of Weibull Self-Similar Tele-traffic Model , 2017 .

[25]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[26]  Fernando Barreto,et al.  Fast emergency paths schema to overcome transient link failures in ospf routing , 2012, ArXiv.

[27]  Matthew Roughan,et al.  The Internet Topology Zoo , 2011, IEEE Journal on Selected Areas in Communications.

[28]  E. Kresch,et al.  A Poisson Based Bursty Model of Internet Traffic , 2011, 2011 IEEE 11th International Conference on Computer and Information Technology.

[29]  Joao Santos,et al.  Performance evaluation of integrated OTN/DWDM networks with single-stage multiplexing of optical channel data units , 2011, 2011 13th International Conference on Transparent Optical Networks.

[30]  Lukás Burget,et al.  Extensions of recurrent neural network language model , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[31]  Klaus Wehrle,et al.  Modeling and Tools for Network Simulation , 2010, Modeling and Tools for Network Simulation.

[32]  Klaus Wehrle,et al.  A Performance Comparison of Recent Network Simulators , 2009, 2009 IEEE International Conference on Communications.

[33]  Irfan-Ullah Awan,et al.  Performance Evaluation of Weighted Fair Queuing System Using Matrix Geometric Method , 2009, Networking.

[34]  A. Afshar,et al.  An MLP neural network for time delay prediction in networked control systems , 2008, 2008 Chinese Control and Decision Conference.

[35]  Michalis Faloutsos,et al.  Long-range dependence ten years of Internet traffic modeling , 2004, IEEE Internet Computing.

[36]  Jun Zhang,et al.  Wavelength converter placement in least-load-routing-based optical networks using genetic algorithms , 2004 .

[37]  Michalis Faloutsos,et al.  A nonstationary Poisson view of Internet traffic , 2004, IEEE INFOCOM 2004.

[38]  Hao Wu,et al.  Large-scale network simulation: how big? how fast? , 2003, 11th IEEE/ACM International Symposium on Modeling, Analysis and Simulation of Computer Telecommunications Systems, 2003. MASCOTS 2003..

[39]  Donald F. Towsley,et al.  On the autocorrelation structure of TCP traffic , 2002, Comput. Networks.

[40]  Sally Floyd,et al.  Difficulties in simulating the internet , 2001, TNET.

[41]  Christopher R. Palmer,et al.  Generating network topologies that obey power laws , 2000, Globecom '00 - IEEE. Global Telecommunications Conference. Conference Record (Cat. No.00CH37137).

[42]  V. Paxson,et al.  Wide-area traffic: the failure of Poisson modeling , 1994, SIGCOMM.

[43]  Leonard Kleinrock,et al.  Analytic and simulation methods in computer network design , 1899, AFIPS '70 (Spring).

[44]  Katrin Baumgartner,et al.  Computer Networks And Systems Queueing Theory And Performance Evaluation , 2016 .

[45]  George F. Riley,et al.  The ns-3 Network Simulator , 2010, Modeling and Tools for Network Simulation.

[46]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[47]  M. F. Kazmi,et al.  Analysis of a finite capacity non preemptive priority queue , 1984, Comput. Oper. Res..

[48]  Tom V. Mathew Genetic Algorithm , 2022 .