Fabien Geyer
ABSTRACT
Understanding the performance of network protocols and communication networks generally relies on expert knowledge and understanding of the different elements of a network, their configuration and the overall architecture and topology. Machine learning is often proposed as a tool to help modeling complex protocols. One drawback of this method is that high-level features are generally used - which require expert knowledge on the network protocols to be chosen, correctly engineered, and measured -- and the approaches are generally limited to a given network topology.
In this paper, we propose a methodology to address the challenge of working with machine learning by using lower-level features, namely only a description of the network architecture. Our main contribution is an approach for applying deep learning on network topologies via the use of Graph Gated Neural Networks, a specialized recurrent neural network for graphs. Our approach enables us to make performance predictions based only on a graph-based representation of network topologies. We apply our approach to the task of predicting the throughput of TCP flows. We evaluate three different traffic models: large file transfers, small file transfers, and a combination of small and large file transfers. Numerical results show that our approach is able to learn the throughput performance of TCP flows with good accuracies larger than 90%, even on larger topologies.
- 2017. ns-2, Network Simulator (ver. 2.35). (2017). Retrieved July 28, 2017 from https://www.isi.edu/nsnam/ns/Google Scholar
- Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dan Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2015. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015). http://tensorflow.org/ Software available from tensorflow.org.Google Scholar
- Luis B. Almeida. 1990. Artificial Neural Networks. IEEE Press, Piscataway, NJ, USA, Chapter A Learning Rule for Asynchronous Perceptrons with Feedback in a Combinatorial Environment, 102--111. Google ScholarDigital Library
- Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral Networks and Locally Connected Networks on Graphs. In Proceedings of the 2nd International Conference on Learning Representations (ICLR'2014).Google Scholar
- Neal Cardwell, Stefan Savage, and Thomas Anderson. 2000. Modeling TCP Latency. In Proceedings of the 19th Annual Joint Conference of the IEEE Computer and Communications Societies (INFOCOM 2000), Vol. 3. IEEE, 1742--1751.Google ScholarCross Ref
- Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. (June 2014). arXiv:1406.1078Google Scholar
- Victor Firoiu, Ikjun Yeom, and Xiaohui Zhang. 2001. A Framework for Practical Performance Evaluation and Traffic Engineering in IP Networks. In Proceedings of the IEEE International Conference on Telecommunications.Google Scholar
- Fabien Geyer, Stefan Schneele, and Georg Carle. 2013. Practical Performance Evaluation of Ethernet Networks with Flow-Level Network Modeling. In Proceedings of the 7th International Conference on Performance Evaluation Methodologies and Tools (VALUETOOLS 2013). 253--262. Google ScholarDigital Library
- Fabien Geyer, Stefan Schneele, and Georg Carle. 2014. PETFEN: A Performance Evaluation Tool for Flow-Level Network Modeling of Ethernet Networks. In Proceedings of the 8th International Conference on Performance Evaluation Methodologies and Tools (VALUETOOLS 2014). Google ScholarDigital Library
- Marco Gori, Gabriele Monfardini, and Franco Scarselli. 2005. A New Model for Learning in Graph Domains. In Proceedings of the 2005 IEEE International joint Conference on Neural Networks (IJCNN'05), Vol. 2. IEEE, 729--734.Google ScholarCross Ref
- Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka, Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette, Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann, Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield, Phil Blunsom, Koray Kavukcuoglu, and Demis Hassabis. 2016. Hybrid computing using a neural network with dynamic external memory. Nature 538, 7626 (Oct. 2016), 471--476.Google ScholarCross Ref
- Mikael Henaff, Joan Bruna, and Yann LeCun. 2015. Deep Convolutional Networks on Graph-Structured Data. (June 2015). arXiv:1506.05163Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-Term Memory. Neural Computation 9, 8 (Nov. 1997), 1735--1780. Google ScholarDigital Library
- Hadrien Hours, Ernst W. Biersack, and Patrick Loiseau. 2016. A Causal Approach to the Study of TCP Performance. ACM Trans. Intel. Syst. Tech. 7, 2 (Jan. 2016), 25:1--25:25. Google ScholarDigital Library
- Diederik Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR'2015). https://arxiv.org/abs/1412.6980Google Scholar
- Cheng Li, Xiaoxiao Guo, and Qiaozhu Mei. 2016. DeepGraph: Graph Structure Predicts Network Growth. (Oct. 2016). arXiv:1610.06251Google Scholar
- Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. 2016. Gated Graph Sequence Neural Networks. In Proceedings of the 4th International Conference on Learning Representations (ICLR'2016).Google Scholar
- Matthew Mathis, Jeffrey Semke, Jamshid Mahdavi, and Teunis Ott. 1997. The Macroscopic Behavior of the TCP Congestion Avoidance Algorithm. ACM SIGCOMM Comput. Commun. Rev. 27, 3 (June 1997), 67--82. Google ScholarDigital Library
- Mariyam Mirza, Joel Sommers, Paul Barford, and Xiaojin Zhu. 2010. A Machine Learning Approach to TCP Throughput Prediction. IEEE/ACM Trans. Netw. 18, 4 (Aug. 2010), 1026--1039. Google ScholarDigital Library
- Jitendra Padhye, Victor Firoiu, Don F. Towsley, and James F. Kurose. 2000. Modeling TCP Reno Performance: A Simple Model and Its Empirical Validation. IEEE/ACM Trans. Netw. 8, 2 (April 2000), 133--145. Google ScholarDigital Library
- Fernando J. Pineda. 1987. Generalization of back-propagation to recurrent neural networks. Phys. Rev. Lett. 59 (Nov. 1987), 2229--2232. Issue 19.Google ScholarCross Ref
- Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2009. Computational Capabilities of Graph Neural Networks. IEEE Trans. Neural Netw. 20, 1 (Jan. 2009), 81--102. Google ScholarDigital Library
- Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2009. The Graph Neural Network Model. IEEE Trans. Neural Netw. 20, 1 (Jan. 2009), 61--80. Google ScholarDigital Library
- Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. 2017. Modeling Relational Data with Graph Convolutional Networks. (March 2017). arXiv:1703.06103Google Scholar
- Nitish Srivastava, Geoffrey E Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research 15, 1 (Jan. 2014), 1929--1958. Google ScholarDigital Library
- Mukarram Bin Tariq, Kaushik Bhandankar, Vytautas Valancius, Amgad Zeitoun, Nick Feamster, and Mostafa Ammar. 2013. Answering "What-If" Deployment and Configuration Questions With WISE: Techniques and Deployment Experience. IEEE/ACM Trans. Netw. 21, 1 (Feb. 2013), 1--13. Google ScholarDigital Library
- Guibin Tian and Yong Liu. 2012. Towards Agile and Smooth Video Adaptation in Dynamic HTTP Streaming. In Proceedings of the 8th International Conference on Emerging Networking Experiments and Technologies (CoNEXT '12). ACM, 109--120. Google ScholarDigital Library
- Tijmen Tieleman and Geoffrey Hinton. 2012. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning 4, 2 (2012), 26--31.Google Scholar
- Pedro Velho, Lucas M. Schnorr, Henri Casanova, and Arnaud Legrand. 2011. Flow-level network models: have we reached the limits? Technical Report 7821. INRIA.Google Scholar
Index Terms
- Performance Evaluation of Network Topologies using Graph-Based Deep Learning
Recommendations
Learning and Generating Distributed Routing Protocols Using Graph-Based Deep Learning
Big-DAMA '18: Proceedings of the 2018 Workshop on Big Data Analytics and Machine Learning for Data Communication NetworksAutomated network control and management has been a long standing target of network protocols. We address in this paper the question of automated protocol design, where distributed networked nodes have to cooperate to achieve a common goal without a ...
DeepComNet: Performance evaluation of network topologies using graph-based deep learning
AbstractModeling the performance of network protocols and communication networks generally relies on expert knowledge and understanding of the different elements of a network, their configuration, and the overall architecture and topology. ...
Evaluation of Deep Learning Models for Network Performance Prediction for Scientific Facilities
SNTA '20: Proceedings of the 3rd International Workshop on Systems and Network Telemetry and AnalyticsLarge data transfers are getting more critical with the increasing volume of data in scientific computing. While scientific facilities manage dedicated infrastructures to support large data transfers, predicting network performance based on the ...
Comments