XAI-on-RAN: Explainable, AI-native, and GPU-Accelerated RAN Towards 6G

TL;DR

This paper introduces xAI-Native, a GPU-accelerated, explainable AI framework for radio access networks, enhancing transparency and performance in high-stakes 6G applications.

Contribution

It presents a novel mathematical framework and a hybrid XAI model tailored for 6G RANs, addressing transparency, latency, and GPU efficiency.

Findings

xAI-Native outperforms baseline models in empirical tests.

The framework effectively balances transparency, latency, and GPU utilization.

Empirical results confirm improved network performance and trustworthiness.

Abstract

Artificial intelligence (AI)-native radio access networks (RANs) will serve vertical industries with stringent requirements: smart grids, autonomous vehicles, remote healthcare, industrial automation, etc. To achieve these requirements, modern 5G/6G design increasingly leverage AI for network optimization, but the opacity of AI decisions poses risks in mission-critical domains. These use cases are often delivered via non-public networks (NPNs) or dedicated network slices, where reliability and safety are vital. In this paper, we motivate the need for transparent and trustworthy AI in high-stakes communications (e.g., healthcare, industrial automation, and robotics) by drawing on 3rd generation partnership project (3GPP)'s vision for non-public networks. We design a mathematical framework to model the trade-offs between transparency (explanation fidelity and fairness), latency, and graphics processing unit (GPU) utilization in deploying explainable AI (XAI) models. Empirical evaluations demonstrate that our proposed hybrid XAI model xAI-Native, consistently surpasses conventional baseline models in performance.