EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An adaptive spatio-temporal framework for carbon-aware and privacy-preserving DNN partitioning

Saanvi Goel, Syamasudha Veeragandham

Frontiers in Artificial Intelligence · 17.11.2026 · 9

DOI: 10.3389/frai.2026.1961682 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Artificial Intelligence, online erschienen am 17.11.2026. Verfasst von Saanvi Goel und 1 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Choosing where to split a deep neural network (DNN) between device and cloud requires balancing latency, carbon emissions, privacy and device thermal state, which existing partitioning methods rarely address jointly.

Methods

We propose GreenSplit, an adaptive spatio-temporal framework that selects the split layer and cloud region by minimising a normalised four-term cost under a hard privacy exclusion zone, with an Adaptive Weight Controller (AWC), current and forecast carbon intensity, Laplace noise on transmitted activations, a thermal-battery model, and a dynamic voltage and frequency scaling (DVFS) safeguard. We evaluated it in simulation on MobileNetV2 across three cloud regions (200 sustained-load trials), extended the decision model to ResNet-50, ViT-Base and the CLIP ViT-B/32 image encoder, and tested the noise mechanism on a pretrained ImageNet MobileNetV2 with 1,000 real images.

Results

Under our assumed energy constants, offloading a lightweight CNN is carbon-costly (5.8–6.7 × on-device carbon), so the framework keeps MobileNetV2 local; it then behaves as local execution with DVFS, emitting 66.0% of the carbon of unmanaged local execution with no privacy-zone violations (4% for baselines without the zone). Its 32.5% throttle rate at nominal thermal parameters is not robust (0–100% over plausible parameters), although DVFS lowers throttling in every draw. Laplace noise at operating budgets (ϵ r ≤ 10 leaves the cloud classifying at chance, while accuracy-preserving budgets ( ϵ r ≈ 3 × 1 0 4 –3 × 10 5 ) allow perfect re-identification among 1,000 images and give a vacuous differential-privacy bound. The AWC's benefit in its original scenario does not transfer to unseen disturbances in its original min–max form; a fixed-scale variant is stable but gives only a modest gain and no thermal benefit.

Discussion

The hard exclusion zone, not the noise, provides utility-preserving protection. All results are simulated; validation on physical devices is required.

Zitieren

APA

Goel, S., & Veeragandham, S. (2026). An adaptive spatio-temporal framework for carbon-aware and privacy-preserving DNN partitioning. Frontiers in Artificial Intelligence, 9. https://doi.org/10.3389/frai.2026.1961682

Vancouver

Goel S, Veeragandham S. An adaptive spatio-temporal framework for carbon-aware and privacy-preserving DNN partitioning. Frontiers in Artificial Intelligence. 2026;9. doi:10.3389/frai.2026.1961682

BibTeX
@article{Goel2026,
  author = {Goel, Saanvi and Veeragandham, Syamasudha},
  title = {An adaptive spatio-temporal framework for carbon-aware and privacy-preserving DNN partitioning},
  journal = {Frontiers in Artificial Intelligence},
  year = {2026},
  volume = {9},
  doi = {10.3389/frai.2026.1961682}
}
Kostenlos starten →