ARCADE: A RAN Diagnosis Methodology in a Hybrid AI Environment for 6G Networks

TL;DR

ARCADE introduces a methodology leveraging hybrid AI architectures to detect and diagnose radio coverage anomalies in 6G networks, advancing network automation and analytics beyond current 5G capabilities.

Contribution

The paper presents ARCADE, a novel anomaly detection methodology that integrates hybrid AI architectures for improved diagnosis in 6G cellular networks.

Findings

Effective detection of radio coverage anomalies

Enhanced AI application through hybrid architecture

Supports network automation in 6G evolution

Abstract

Artificial Intelligence (AI) plays a key role in developing 6G networks. While current specifications already include Network Data Analytics Function (NWDAF) as a network element responsible for providing information about the core, a more comprehensive approach will be needed to enable automation of network segments that are not yet fully explored in the context of 5G. In this paper, we present Automated Radio Coverage Anomalies Detection and Evaluation (ARCADE), a methodology for identifying and diagnosing anomalies in the cellular access network. Furthermore, we demonstrate how a hybrid architecture of network analytics functions in the evolution toward 6G can enhance the application of AI in a broader network context, using ARCADE as a practical example of this approach.