ABSTRACT
Recent trends in networking are proposing the use of Machine Learning (ML) techniques for the control and operation of the network. In this context, ML can be used as a computer network modeling technique to build models that estimate the network performance. Indeed, network modeling is a central technique to many networking functions, for instance in the field of optimization, in which the model is used to search a configuration that satisfies the target policy. In this paper, we aim to provide an answer to the following question: Can neural networks accurately model the delay of a computer network as a function of the input traffic? For this, we assume the network as a black-box that has as input a traffic matrix and as output delays. Then we train different neural networks models and evaluate its accuracy under different fundamental network characteristics: topology, size, traffic intensity and routing. With this, we aim to have a better understanding of computer network modeling with neural nets and ultimately provide practical guidelines on how such models need to be trained.
- Clark, D., et al. "A knowledge plane for the internet." Conf. on Applications, technologies, architectures, and protocols for computer communications, ACM Proceedings of, 2003. Google ScholarDigital Library
- Kreutz, D., et al. "Software-defined networking: A comprehensive survey." Proceedings of the IEEE vol. 103.1, pp. 14--76, 2015.Google ScholarCross Ref
- Clemm, A., et al. "DNA: An SDN framework for distributed network analytics," Integrated Network Management (IM), IFIP/IEEE International Symposium on. IEEE, 2015.Google Scholar
- Mestres, A., Rodriguez-Natal, A., Carner, J., Barlet, P., Alarcón, E., Meyer, D., Barkai, S., Maino, F., Ermagan, V., Coras, F., Latapie, H., Cassar, C., Evans, J., Muntes, V., Walrand, J., Cabellos, A., "Knowledge- Defined Networking.", ACM Sigcomm Computer Communication Review, vol. 47.3, pp. 2--10, 2017. Google ScholarDigital Library
- Wang, Ning, et al. "An overview of routing optimization for internet traffic engineering." IEEE Communications Surveys & Tutorials 10.1, 2008. Google ScholarDigital Library
- Simon, Gyula, et al. "Simulation-based optimization of communication protocols for large-scale wireless sensor networks." IEEE aerospace conference, Vol. 3. 2003.Google Scholar
- Giambene, G., "Queuing Theory and Telecommunications: Networks and Applications." Springer Science& Business Media, 2005. Google ScholarDigital Library
- Shortle, John F., et al. "Fundamentals of queueing theory." John Wiley & Sons, 2018.Google Scholar
- Steinbach, T, et al. "An extension of the OMNeT++ INET framework for simulating real-time ethernet with high accuracy." Proc. of the 4th Int. ICST Conference on Simulation Tools and Techniques, 2011. Google ScholarDigital Library
- Dainotti, A., et al. "Issues and future directions in traffic classification." IEEE network, vol. 26.1, 2012. Google ScholarDigital Library
- Sommer, R., and Vern P.. "Outside the closed world: On using machine learning for network intrusion detection." Security and Privacy (SP), IEEE Symposium on. IEEE, 2010. Google ScholarDigital Library
- Yan, He, et al. "G-rca: a generic root cause analysis platform for service quality management in large ip networks." IEEE/ACM Transactions on Networking, vol. 20.6, pp. 1734--1747, 2012. Google ScholarDigital Library
- Lin, Shih-Chun, et al. "QoS-aware adaptive routing in multi-layer hierarchical software defined networks: a reinforcement learning approach." Services Computing (SCC), IEEE International Conference on, 2016.Google Scholar
- Wang, Mowei, et al. "Machine Learning for Networking: Workflow, Advances and Opportunities." IEEE Network, 2017.Google Scholar
- Varga, A. "The OMNeT++ discrete event simulation system." Proceedings of the European simulation multiconference, Vol. 9, No. S 185, 2001.Google Scholar
- Medina, Alberto, et al. "Traffic matrix estimation: Existing techniques and new directions." ACM SIGCOMM Computer Communication Review, vol. 32.4, pp. 161--174, 2002. Google ScholarDigital Library
- Anthony, Martin, and Peter L. Bartlett. "Neural network learning: Theoretical foundations." cambridge university press, 2009. Google ScholarDigital Library
- Understanding the Modeling of Computer Network Delays using Neural Networks
Recommendations
Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
SOSR '19: Proceedings of the 2019 ACM Symposium on SDN ResearchNetwork modeling is a critical component for building self-driving Software-Defined Networks, particularly to find optimal routing schemes that meet the goals set by administrators. However, existing modeling techniques do not meet the requirements to ...
Investigating the possibility of speeding up Mininet by using Netmap, an alternative Linux packet I/O framework
AbstractA new networking paradigm known as software-defined networking (SDN) is making managing IP networks easier. As adoption of the paradigm increases, there is an increasing need to adapt existing applications to work with it, and to invent new ...
Software-Defined Networking: On the Verge of a Breakthrough?
Many experts predict that software-defined networking, a technology that's been highly touted for several years, will soon finally begin gaining ground in the marketplace.
Comments