analiza aiqbench
This research introduces KAC, a multimodal anomaly detection framework specifically designed to address the challenges of 5G and Open RAN observability by integrating operator-style textual summaries with full temporal KPI evidence. The approach demonstrates robust performance on real-world telecom benchmarks, including Nokia production traces, effectively handling severe class imbalance while maintaining strict alert budgets for future self-optimizing networks.
KPI-Aware Multimodal Anomaly Detection for 5G and Open RAN Telemetry
arXiv:2610.25510v1 Announce Type: new Abstract: Reliable anomaly detection is a deployment bottleneck for 5G/Open RAN observability and emerging self-optimizing 6G systems, where hundreds of heterogeneous KPIs, severe class imbalance, and strict alert budgets make purely numerical scores brittle. We present KAC, a deployment-oriented KPI-aware multimodal anomaly-detection framework that uses KPI-level residual-text alignment to turn compact operator-style summaries into a learnable feedback signal over full-KPI temporal evidence. This gives the detector broad numerical coverage like modern time-series models, while retaining the sparse KPI-specific reasoning that makes operator feedback sustainable in a future operator-facing workflow. Across public telecom telemetry, enterprise-scale Open RAN observability data, and a Nokia benchmark built from real 5G RAN production packet traces with realism-hardened injected anomalies, KAC achieves strong threshold-based detection performance while remaining competitive on threshold-free ranking metrics. On TelecomTS, at a fixed 2.5 percent false-positive-rate operating point, KAC achieves the highest recall among the evaluated residual-based methods while maintaining comparable precision; across the evaluated benchmarks, it remains robust under substantial class imbalance. KAC is integrated in pre-production shadow mode with Nokia's GKE-based KPI construction pipeline, where it continuously scores telemetry windows alongside an internal packet-level anomaly detector for operational evaluation.
Abstract:Reliable anomaly detection is a deployment bottleneck for 5G/Open RAN observability and emerging self-optimizing 6G systems, where hundreds of heterogeneous KPIs, severe class imbalance, and strict alert budgets make purely numerical scores brittle. We present KAC, a deployment-oriented KPI-aware multimodal anomaly-detection framework that uses KPI-level residual-text alignment to turn compact operator-style summaries into a learnable feedback signal over full-KPI temporal evidence. This gives the detector broad numerical coverage like modern time-series models, while retaining the sparse KPI-specific reasoning that makes operator feedback sustainable in a future operator-facing workflow. Across public telecom telemetry, enterprise-scale Open RAN observability data, and a Nokia benchmark built from real 5G RAN production packet traces with realism-hardened injected anomalies, KAC achieves strong threshold-based detection performance while remaining competitive on threshold-free ranking metrics. On TelecomTS, at a fixed 2.5 percent false-positive-rate operating point, KAC achieves the highest recall among the evaluated residual-based methods while maintaining comparable precision; across the evaluated benchmarks, it remains robust under substantial class imbalance. KAC is integrated in pre-production shadow mode with Nokia's GKE-based KPI construction pipeline, where it continuously scores telemetry windows alongside an internal packet-level anomaly detector for operational evaluation.
Machine Learning (cs.LG)
arXiv:2610.25510 [cs.LG]
(or arXiv:2610.25510v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.25510 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 281 cuvinte
Subiecte conexe
Sparse Evidence Can Suffice: Agentic Evidence Seeking for Multimodal Video Misinformation Detection
arXiv · 21 iul. 2026
Towards robust multimodal 3D object detection via visual foundation models
arXiv · 22 sept. 2026
Focus on What You Need: Global-to-Local Dynamic Attention for Multimodal Sarcasm Detection
arXiv · 14 oct. 2026
From Recognition to Reasoning: Advancing Multimodal Harmful Meme Detection via Chain-of-Thought Alignment
arXiv · 25 aug. 2026