Towards Reliable AI in 6G: Detecting Concept Drift in Wireless Network
This addresses the reliability of AI in 6G networks for telecom operators and users, though it is incremental as it builds on existing drift detection methods with specific improvements.
The paper tackled the problem of concept drift degrading AI model accuracy in non-stationary 6G wireless networks by introducing two unsupervised, model-agnostic drift detectors, which outperformed classical detectors by 20-40 percentage points and achieved F1-scores up to 1.00 with reduced false alarms.
AI-native 6G networks promise unprecedented automation and performance by embedding machine-learning models throughout the radio access and core segments of the network. However, the non-stationary nature of wireless environments due to infrastructure changes, user mobility, and emerging traffic patterns, induces concept drifts that can quickly degrade these model accuracies. Existing methods in general are very domain specific, or struggle with certain type of concept drift. In this paper, we introduce two unsupervised, model-agnostic, batch concept drift detectors. Both methods compute an expected-utility score to decide when concept drift occurred and if model retraining is warranted, without requiring ground-truth labels after deployment. We validate our framework on two real-world wireless use cases in outdoor fingerprinting for localization and for link-anomaly detection, and demonstrate that both methods are outperforming classical detectors such as ADWIN, DDM, CUSUM by 20-40 percentage points. Additionally, they achieve an F1-score of 0.94 and 1.00 in correctly triggering retraining alarm, thus reducing the false alarm rate by up to 20 percentage points compared to the best classical detectors.