Learning Hidden QoS Structures in Cellular Networks: A Context-Aware Benchmark of Unsupervised Clustering Methods with a New QoS Cluster Validity Protocol

The launch of sixth-generation (6G) mobile networks is expected to introduce significant variability in Quality of Service (QoS), driven by environmental conditions, traffic heterogeneity, device diversity, and network slicing policies. Existing clustering-based QoS analysis methods rely primarily on using only KPI variables, such as latency, throughput, jitter and packet loss datasets, and classical geometric validity metrics, providing limited insight into the stability, predictive capability, and operational relevance of discovered clusters. To address these limitations, this study proposes a context-aware QoS modelling framework and a unified network-centric cluster evaluation protocol. A dataset comprising 2345 observations is constructed by integrating QoS indicators with contextual and operational variables, including weather conditions, time of day, geographic region, traffic type, device class, and slice identity. Four clustering paradigms, k-means, DBSCAN, spectral clustering, and Deep Embedded Clustering (DEC), are evaluated using both classical metrics and three proposed evaluation measures: Contextual Cluster Stability (CCS), QoS-Regime Predictive Consistency (QPC), and Slice-Level Reliability Separation (SLRS). The results demonstrate that classical clustering metrics alone are insufficient for assessing QoS regime quality. While DEC achieves strong structural performance in latent space, all methods exhibit near-zero predictive consistency and weak reliability separation. These findings reveal a consistent divergence between structural clustering quality and operational usefulness, indicating that unsupervised clustering alone is insufficient for QoS prediction and reliability-aware decision-making. The proposed framework provides a foundation for evaluating clustering methods in context-sensitive network environments and highlights the need for integrating temporal modelling and reliability-aware learning in future 6G network optimisation systems.