Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN

Abstract

Network 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 provide accurate estimations of relevant performance metrics such as delay and jitter. In this paper we propose a novel Graph Neural Network (GNN) model able to understand the complex relationship between topology, routing and input traffic to produce accurate estimates of the per-source/destination pair mean delay and jitter. GNN are tailored to learn and model information structured as graphs and as a result, our model is able to generalize over arbitrary topologies, routing schemes and variable traffic intensity. In the paper we show that our model provides accurate estimates of delay and jitter (worst case $R^2=0.86$) when testing against topologies, routing and traffic not seen during training. In addition, we present the potential of the model for network operation by presenting several use-cases that show its effective use in per-source/destination pair delay/jitter routing optimization and its generalization capabilities by reasoning in topologies and routing schemes not seen during training.

arXiv comment12 pages

References in corpus (10)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Explaining and Harnessing Adversarial Examples
• Neural Message Passing for Quantum Chemistry
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Self-Normalizing Neural Networks
• Machine Learning for Networking: Workflow, Advances and Opportunities
• Knowledge-Defined Networking
• Experience-driven Networking: A Deep Reinforcement Learning based Approach
• Message-Passing Neural Networks Learn Little's Law
• Fast emergency paths schema to overcome transient link failures in ospf routing

Cited by in corpus (18)

• Graph Neural Networks: A Review of Methods and Applications
• RouteNet: Leveraging Graph Neural Networks for network modeling and optimization in SDN
• Graph-based Deep Learning for Communication Networks: A Survey
• Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case
• Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking
• RouteNet-Fermi: Network Modeling with Graph Neural Networks
• Interpreting Deep Learning-Based Networking Systems
• MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineering
• GDDR: GNN-based Data-Driven Routing
• The Graph Neural Networking Challenge: A Worldwide Competition for Education in AI/ML for Networks
• IGNNITION: Bridging the Gap Between Graph Neural Networks and Networking Systems
• Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks
• Detecting Contextual Network Anomalies with Graph Neural Networks
• QT-Routenet: Improved GNN generalization to larger 5G networks by fine-tuning predictions from queueing theory
• Proactive Defense for Internet-of-Things: Integrating Moving Target Defense with Cyberdeception
• Low Complexity Approaches for End-to-End Latency Prediction
• Scaling Graph-based Deep Learning models to larger networks
• Time-based Dynamic Controllability of Disjunctive Temporal Networks with Uncertainty: A Tree Search Approach with Graph Neural Network Guidance