Applying Graph-based Deep Learning To Realistic Network Scenarios
This addresses the need for fast and accurate network modeling tools for functional optimization in networking, though it appears incremental as it builds on existing graph-based deep learning approaches.
The paper tackles the problem of accurately estimating per-path mean delay in realistic network scenarios with complex queue scheduling, which existing ML-based methods fail to do, and presents a graph-based deep learning model that generalizes across unseen topologies, routing, policies, and traffic matrices.
Recent advances in Machine Learning (ML) have shown a great potential to build data-driven solutions for a plethora of network-related problems. In this context, building fast and accurate network models is essential to achieve functional optimization tools for networking. However, state-of-the-art ML-based techniques for network modelling are not able to provide accurate estimates of important performance metrics such as delay or jitter in realistic network scenarios with sophisticated queue scheduling configurations. This paper presents a new Graph-based deep learning model able to estimate accurately the per-path mean delay in networks. The proposed model can generalize successfully over topologies, routing configurations, queue scheduling policies and traffic matrices unseen during the training phase.