RGCN for Beyond Pairwise Training: Generalizing Monitors Selection in Network Tomography

In the dynamic field of 5G network monitoring, the ability to generalize monitors' placement across a network is crucial for comprehensive coverage. This study introduces the use of the Relational Graph Convolutional Network (RGCN) model to meet this challenge. We conducted a comparative analysis between the RGCN and a traditional Neural Network (NN) across two network topologies, considering every possible node configuration within these topologies. Our findings indicate that the RGCN model, once trained on a specific node pair, exhibits superior generalization ability and accuracy. It consistently transfers its learning to changes in monitors' placement and accurately estimates links delays beyond its initial training monitors. Unlike the NN, which showed significant limitations in generalizing monitors' placement and high error rates. This paper not only demonstrates the effectiveness of the RGCN model in generalizing the monitors' placement problem but also paves the way for its broader application in dynamic network monitorinf contexts.

I. Introduction

In the evolving world of telecommunications, the advancements introduced by 5G networks bring to the forefront the limitations of traditional network monitoring methods, especially in terms of scalability, flexibility, and the significant costs associated with the deployment and maintenance of monitoring equipments. Characterized by their heterogeneity, 5G networks integrate diverse technologies, such as small cells, macro cells, and edge computing units. This diversity, while enabling a wide range of services and applications, complicates the task of comprehensive network monitoring. Moreover, 5G's need for accurate, non-intrusive monitoring is critical to support URLLC applications like autonomous vehicles.