EUVIMEDEUVIMED entdecken
Crossref

Budget-Aware Edge-First Collaboration for Robust Inference in Sensor–Cloud Networks

Malka N. Halgamuge, Ibrahim Khalil, Iqbal Gondal, Alireza Jolfaei, Narayan Srinivasa

IEEE Network · 2026-05 · 40 (3) · 121-129

DOI: 10.1109/mnet.2026.3671221 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Network, 2026-05. Verfasst von Malka N. Halgamuge und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Edge-enabled sensing applications in digital health, industrial Internet of Things (IIoT), and extended reality (XR) face a persistent trilemma: lightweight edge models meet strict latency, bandwidth, and energy budgets but degrade under noise and distribution shift; cloud models improve robustness and calibration but can violate tail-latency and privacy constraints; and naïve split inference reduces edge compute at the cost of inflated network usage and unstable tails. We present a deployable, edge-first blueprint for bud-get-aware collaborative training and co-inference between large cloud models and lightweight edge models in sensor-cloud networks. The design has three pillars: (i) a collaborative training workflow that transfers robustness and calibrated confidence from a cloud teacher to an edge student so most inference completes locally; (ii) a confidence-gated, budget-aware router that selects among EDGE, EDGE + CORRECTION, and CLOUD actions using calibrated uncertainty and short-horizon link telemetry while explicitly enforcing P95 latency, bandwidth, and energy budgets; and (iii) privacy scaffolding via trusted execution environments (and optional differential privacy), with all correction or offload overheads accounted end-to-end when invoked. Compact case studies on inertial and physiological sensing workloads demonstrate edge-dominant operation with tight latency tails, small and predictable bandwidth, bounded energy consumption, and improved robustness over non-collaborative baselines. We conclude with practical guidance on system design, scheduling, measurement, and deployment trade-offs for realworld sensor-cloud intelligence.

Zitieren

APA

Halgamuge, M. N., Khalil, I., Gondal, I., Jolfaei, A., & Srinivasa, N. (2026). Budget-Aware Edge-First Collaboration for Robust Inference in Sensor–Cloud Networks. IEEE Network, 40(3), 121-129. https://doi.org/10.1109/mnet.2026.3671221

Vancouver

Halgamuge MN, Khalil I, Gondal I, Jolfaei A, Srinivasa N. Budget-Aware Edge-First Collaboration for Robust Inference in Sensor–Cloud Networks. IEEE Network. 2026;40(3):121-129. doi:10.1109/mnet.2026.3671221

BibTeX
@article{Halgamuge2026,
  author = {Halgamuge, Malka N. and Khalil, Ibrahim and Gondal, Iqbal and Jolfaei, Alireza and Srinivasa, Narayan},
  title = {Budget-Aware Edge-First Collaboration for Robust Inference in Sensor–Cloud Networks},
  journal = {IEEE Network},
  year = {2026},
  volume = {40},
  number = {3},
  pages = {121--129},
  doi = {10.1109/mnet.2026.3671221}
}
Kostenlos starten →