Uncovering Issues in the Radio Access Network by Looking at the Neighbors

2025-04-20

AI Summary

In large-scale, multi-generation (2G–5G) radio access networks (RANs), mobility-induced disturbances severely impair the accuracy of anomaly detection during operations and maintenance. Method: This paper proposes an unsupervised graph neural network (GNN) approach grounded in local neighborhood context. It constructs a spatiotemporal graph to model cells and their dynamically evolving neighborhood relationships, explicitly decoupling internal faults (e.g., misconfigurations, hardware failures) from external mobility perturbations. A novel neighborhood-context encoding paradigm is introduced to enable cross-regional generalization. Contribution/Results: The method defines long-duration anomalies and quantifies intervention necessity—45.95% require manual verification. Evaluated on real-world data from 7,890 cells over three months, it achieves strong generalization; human validation confirms that 87.3% of detected long-duration anomalies correspond to genuine faults, significantly improving operational focus and efficiency.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Mobile network operators (MNOs) manage Radio Access Networks (RANs) with massive amounts of cells over multiple radio generations (2G-5G). To handle such complexity, operations teams rely on monitoring systems, including anomaly detection tools that identify unexpected behaviors. In this paper, we present c-ANEMON, a Contextual ANomaly dEtection MONitor for the RAN based on Graph Neural Networks (GNNs). Our solution captures spatio-temporal variations by analyzing the behavior of individual cells in relation to their local neighborhoods, enabling the detection of anomalies that are independent of external mobility factors. This, in turn, allows focusing on anomalies associated with network issues (e.g., misconfigurations, equipment failures). We evaluate c-ANEMON using real-world data from a large European metropolitan area (7,890 cells; 3 months). First, we show that the GNN model within our solution generalizes effectively to cells from previously unseen areas, suggesting the possibility of using a single model across extensive deployment regions. Then, we analyze the anomalies detected by c-ANEMON through manual inspection and define several categories of long-lasting anomalies (6+ hours). Notably, 45.95% of these anomalies fall into a category that is more likely to require intervention by operations teams.

Problem

• Detects RAN anomalies using GNNs and neighbor cell analysis
• Identifies network issues like misconfigurations and equipment failures
• Generalizes model for large-scale deployment across unseen areas

Innovation

• Uses Graph Neural Networks for anomaly detection
• Analyzes cell behavior in local neighborhoods
• Detects anomalies independent of external mobility