Machine Learning-Driven Anomaly Detection for 5G O-RAN Performance Metrics

2025-09-03

AI Summary

In 5G/6G networks, user equipment (UE) throughput degradation and frequent handover failures undermine service reliability, while conventional passive network operations fail to meet stringent high-availability requirements. Method: This paper proposes a lightweight, near-real-time, machine learning–driven anomaly detection framework tailored for the O-RAN architecture. It fuses multi-dimensional KPIs—including resource block utilization, reference signal received power (RSRP), and signal-to-interference-plus-noise ratio (SINR)—collected via open RAN interfaces, and designs two deployable models: (1) a throughput degradation risk identification model for UEs, and (2) a neighboring cell coverage quality anomaly filtering model. Contribution/Results: The framework enables end-to-end proactive fault prevention, supporting precise handover decision-making. It reduces invalid handover candidate cells by 41.27% on average, significantly lowering handover failure rates and the probability of abrupt throughput drops—providing a practical technical pathway toward self-healing, autonomous 6G networks.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Algorithm Configuration

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

The ever-increasing reliance of critical services on network infrastructure coupled with the increased operational complexity of beyond-5G/6G networks necessitate the need for proactive and automated network fault management. The provision for open interfaces among different radio access network,(RAN) elements and the integration of AI/ML into network architecture enabled by the Open RAN,(O-RAN) specifications bring new possibilities for active network health monitoring and anomaly detection. In this paper we leverage these advantages and develop an anomaly detection framework that proactively detect the possible throughput drops for a UE and minimize the post-handover failures. We propose two actionable anomaly detection algorithms tailored for real-world deployment. The first algorithm identifies user equipment (UE) at risk of severe throughput degradation by analyzing key performance indicators (KPIs) such as resource block utilization and signal quality metrics, enabling proactive handover initiation. The second algorithm evaluates neighbor cell radio coverage quality, filtering out cells with anomalous signal strength or interference levels. This reduces candidate targets for handover by 41.27% on average. Together, these methods mitigate post-handover failures and throughput drops while operating much faster than the near-real-time latency constraints. This paves the way for self-healing 6G networks.

Problem

• Proactively detecting throughput drops for UE
• Minimizing post-handover failures in 5G/6G networks
• Developing actionable anomaly detection algorithms for O-RAN

Innovation

• ML-driven anomaly detection for 5G O-RAN
• Proactive UE throughput drop detection algorithm
• Neighbor cell quality filtering reduces handover targets