PRISM

Abstract

Cloud-native 5G core networks span service, orchestration, and infrastructure layers, each producing telemetry in different formats, at different rates, with different semantics. Yet monitoring tools operate per layer, leaving operators without cross-layer visibility needed to diagnose faults that cascade across architectural boundaries. We present PRISM, the first-of-its-kind cross-layer observability framework designed to plug into existing cloud-native cellular core network deployments, capturing evolving structural and temporal dependencies. PRISM collects and correlates logs, metrics, and configuration state from three layers into a unified, continuously updated representation, using an ontology-driven temporal knowledge graph (TKG) as core data structure. To support fault investigation, PRISM provides an incident-time subgraph extraction algorithm that, given incident time and rollback window, produces a compact diagnostic view of the TKG by highlighting anomalous entities and dependency paths connecting them. We evaluate PRISM on an Open5GS 5G core deployment under four fault scenarios spanning resource stress and configuration changes. Across all scenarios, PRISM produces operator-usable incident-time subgraphs that capture dominant anomalous components and their dependency structure, enabling focused troubleshooting and accelerating issue resolution time in virtualized mobile core networks.