titleAPEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations
authorsSwadhin Pradhan, Niloo Bahadori, Peiman Amini
date2026-06-10
venuearXiv (preprint, not peer reviewed)
idarXiv:2606.11553
affiliationCisco
upvotes1 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf
abstractGeneric time-series foundation models transfer poorly to wireless network telemetry whose signals are bursty, zero-inflated, and coupled across protocol layers. We present APEX, a network-native, decoder-only transformer for forecasting enterprise AP telemetry, and evaluate it on DHCP degradation as a representative network task. APEX is pre-trained on 10-channel multivariate telemetry from ~4,500 production wireless networks (~100K AP time series, 34 metrics per AP), and is available as APEX-Large (269M, cloud) and APEX-Edge (10.5M, edge). On a 192-step (4-day) DHCP degradation benchmark, APEX-Large reduces MAE by 18% over the strongest foundation-model baseline (Toto) and 38% over SARIMA, with anomaly-detection F1 = 0.93, while APEX-Edge enables sub-second, privacy-preserving inference on AP-class edge hardware. These results suggest network-native pre-training is a practical foundation for proactive wireless operations.

cite

@misc{pradhan2026apex,
  title={APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations},
  author={Swadhin Pradhan and Niloo Bahadori and Peiman Amini},
  year={2026},
  eprint={2606.11553},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.11553}
}