Diffusion-Based Stress Testing of Overload Monitoring for Resilient Emergency Cellular Networks Using Internet CDR Proxies

2026-10-03

AI Summary

This study addresses the vulnerability of overload detection thresholds in disaster scenarios, where privacy restrictions limit access to fine-grained signaling data and coarse-grained Call Detail Records (CDRs) serve as inadequate proxies. Using internet CDRs as stress proxies, this work employs diffusion models to synthesize realistic traffic surge samples, revealing a threshold drift problem obscured by matched-condition training. To overcome this, it proposes a reusable pre-deployment stress testing framework integrating hard-sample adaptation with convolutional neural networks. The proposed framework significantly enhances system robustness, elevating the F1 score from 0% under default thresholds to 85.67% while achieving an ROC-AUC of 0.99996, thereby effectively restoring critical system alerting capabilities during extreme network congestion events.

Abstract

Disasters can overload cellular control-plane signaling within minutes, yet fine-grained Radio Resource Control (RRC) or Next Generation (NG) Application Protocol (NGAP) telemetry is privacy-sensitive and costly to collect for analytics. Many emergency monitoring pipelines therefore rely on coarse Call Detail Record (CDR) aggregates. We treat Internet activity in CDR grids as a practical proxy for hidden signaling stress under that constraint. We train a lightweight convolutional neural network (CNN) on stylized overload injections, stress-test it with diffusion-synthesized surges that preserve normal traffic structure, and adapt the detector by retraining on hard synthetic samples. Under stress-test conditions, the default alert threshold fails even though receiver operating characteristic (ROC) curves stay strong: the detector still assigns overloaded cells a larger overload probability than normal cells, but those probabilities fall below the default cutoff 0.5 and are labeled normal, so the F1-maximizing threshold -- selected post hoc on the same stress-test grids (oracle $\tau^*$) -- shifts by $0.32 \pm 0.03$ (operating-point drift). Across three random seeds, hard-sample adaptation raises thresholded performance (F1) from 0% (no alerts at the default cutoff 0.5 on any seed) to $85.67 \pm 14.37$% and ranking from ROC-AUC $0.886 \pm 0.040$ to $0.99996 \pm 0.00007$. Diffusion-synthesized surges expose threshold fragility that matched-condition training -- training and testing on the same stylized injections -- hides, and hard-sample adaptation restores usable alerts at the default cutoff. Together, these steps define a reusable pre-deployment stress test for emergency monitors. Internet-only CDR input further supports lightweight AI-native workflows that combine monitoring, recalibration, and adaptation.

Problem

• cellular network overload
• stress testing
• call detail records
• emergency monitoring
• threshold fragility

Innovation

• Diffusion-synthesized stress testing
• CDR proxies
• Hard-sample adaptation
• Lightweight CNN
• Threshold fragility