Packet-Window Anomaly Detection at the Edge: Latency and Energy Trade-Offs of a Distilled Transformer
Sensors · 19.11.2026 · 26 (22) · 7306
DOI: 10.3390/s26227306 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 19.11.2026. Verfasst von Giuseppe Soriano und 2 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Deploying Transformer-based anomaly detection at the network edge requires jointly configuring input representation and model execution under monitoring and resource constraints. We characterize the encoder–regressor component of a previously defined distilled MiniLM packet-window detector, linking token budget, packet-window stride, and device operating mode to detection quality, scoring capacity, and energy cost. Using 5GAD-2022 and NVIDIA Jetson Nano and Xavier NX, we characterize four token budgets across five device–power-mode configurations through detection metrics, mean inference latency from 14.2 to 466.6 ms, latency distributions, and internal input-rail energy from 0.265 to 2.840 J per evaluated window. The analysis reveals diminishing detection gains as token budget increases while execution cost continues to grow, making representation budget a practical deployment control. Power-mode scaling introduces a platform-dependent trade-off: faster execution increases energy per decision on Nano, whereas Xavier NX provides substantial latency reductions with comparatively small energy changes. We translate these measurements into operating envelopes and configuration-selection criteria that relate model scoring capacity to packet-window stride and monitoring demand. Detection quality supplies a task-specific reference; the separate supervised classification head is outside the execution boundary. The resulting analysis provides a quantitative framework for configuring a Transformer-based anomaly-sensing component within an edge monitoring architecture, identifying how representation and execution choices can be coordinated to satisfy application requirements.
Zitieren
APA
Soriano, G., Tonellotto, N., & Gotta, A. (2026). Packet-Window Anomaly Detection at the Edge: Latency and Energy Trade-Offs of a Distilled Transformer. Sensors, 26(22), 7306. https://doi.org/10.3390/s26227306
Vancouver
Soriano G, Tonellotto N, Gotta A. Packet-Window Anomaly Detection at the Edge: Latency and Energy Trade-Offs of a Distilled Transformer. Sensors. 2026;26(22):7306. doi:10.3390/s26227306
BibTeX
@article{Soriano2026,
author = {Soriano, Giuseppe and Tonellotto, Nicola and Gotta, Alberto},
title = {Packet-Window Anomaly Detection at the Edge: Latency and Energy Trade-Offs of a Distilled Transformer},
journal = {Sensors},
year = {2026},
volume = {26},
number = {22},
pages = {7306},
doi = {10.3390/s26227306}
}
EUVIMED