Work

AutoNetTest: A Platform-Aware Framework for Intelligent 5G Network Test Automation and Issue Diagnosis

Year: 2025

Type: conference-paper

Abstract: The rapid evolution of 5G networks introduces intricate challenges in testing and diagnosis, necessitating effective solutions for robust operation. We introduce AutoNetTest, a groundbreaking framework that streamlines test automation through intelligent, platform-aware design. This framework integrates sophisticated machine learning methodologies, allowing for automatic detection of network issues and facilitating thorough diagnostics. With its modular architecture, AutoNetTest is capable of adapting to a variety of platforms, ensuring flexibility in diverse environments. Real-time data analytics play a crucial role in the system, enabling continuous monitoring of network performance and timely anomaly detection. By utilizing both supervised and unsupervised learning techniques, the framework efficiently classifies issues and offers actionable remediation strategies, underscoring a proactive approach to network quality management.

Source: International Conference on Electronic Communication and Artificial Intelligence (ICECAI)

DOI: 10.1109/icecai66283.2025.11171124

Author: Tongwei Tu

Institutions: Embry-Riddle Aeronautical University Daytona Beach Florida Campus, Embry–Riddle Aeronautical University

Language: English

Topic: Software-Defined Networks and 5G

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: green

OpenAlex ID: W4414605201