X-GRL: An Empirical Assessment of Explainable GNN-DRL in B5G/6G Networks

Farhad Rezazadeh, Sergio Barrachina-Munoz, Engin Zeydan, Houbing Song, K. P. Subbalakshmi, Josep Mangues-Bafalluy

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

The rapid development of artificial intelligence (AI) techniques has triggered a revolution in beyond fifth-generation (B5G) and upcoming sixth-generation (6G) mobile networks. Despite these advances, efficient resource allocation in dynamic and complex networks remains a major challenge. This paper presents an experimental implementation of deep reinforcement learning (DRL) enhanced with graph neural networks (GNNs) on a real 5G testbed. The method addresses the explainability of GNNs by evaluating the importance of each edge in determining the model's output. The custom sampling functions feed the data into the proposed GNN-driven Monte Carlo policy gradient (REINFORCE) agent to optimize the gNodeB (gNB) radio resources according to the specific traffic demands. The demo demonstrates real-time visualization of network parameters and superior performance compared to benchmarks.

Original languageEnglish
Title of host publication2023 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2023 - Proceedings
EditorsFrank H.P. Fitzek, Larry Horner, Molka Gharbaoui, Giang Nguyen, Rentao Gu, Tobias Meuser
Pages172-174
Number of pages3
ISBN (Electronic)9798350302547
DOIs
StatePublished - 2023
Event2023 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2023 - Dresden, Germany
Duration: 7 Nov 20239 Nov 2023

Publication series

Name2023 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2023 - Proceedings

Conference

Conference2023 IEEE Conference on Network Function Virtualization and Software Defined Networks, NFV-SDN 2023
Country/TerritoryGermany
CityDresden
Period7/11/239/11/23

Keywords

  • AI/ML
  • B5G/6G
  • GNN-DRL
  • Resource Allocation
  • XAI

Fingerprint

Dive into the research topics of 'X-GRL: An Empirical Assessment of Explainable GNN-DRL in B5G/6G Networks'. Together they form a unique fingerprint.

Cite this