11th EAI International Conference on Performance Evaluation Methodologies and Tools

Research Article

Performance Evaluation of Network Topologies using Graph-Based Deep Learning

  • @INPROCEEDINGS{10.4108/eai.5-12-2017.2274341,
        author={Fabien  Geyer},
        title={Performance Evaluation of Network Topologies using Graph-Based Deep Learning},
        proceedings={11th EAI International Conference on Performance Evaluation Methodologies and Tools},
        publisher={ACM},
        proceedings_a={VALUETOOLS},
        year={2018},
        month={8},
        keywords={network performance evaluation graph neural network deep learning},
        doi={10.4108/eai.5-12-2017.2274341}
    }
    
  • Fabien Geyer
    Year: 2018
    Performance Evaluation of Network Topologies using Graph-Based Deep Learning
    VALUETOOLS
    ACM
    DOI: 10.4108/eai.5-12-2017.2274341
Fabien Geyer1,*
  • 1: Technical University of Munich
*Contact email: fgeyer@net.in.tum.de

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.