# Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled Hardware

arXiv: https://arxiv.org/abs/2609.04705 · HTML: https://mlsanity.com/paper/2609.04705/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [RDD2022: A multi-national image dataset for automatic Road Damage Detection](https://mlsanity.com/paper/2209.08538/) (2022)
- [Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime](https://mlsanity.com/paper/2207.08820/) (2022)
- [Performance Characterization of using Quantization for DNN Inference on Edge Devices: Extended Version](https://mlsanity.com/paper/2303.05016/) (2023)
- [Energy-Efficient Computation with DVFS using Deep Reinforcement Learning for Multi-Task Systems in Edge Computing](https://mlsanity.com/paper/2409.19434/) (2024)
- [SparseDVFS: Sparse-Aware DVFS for Energy-Efficient Edge Inference](https://mlsanity.com/paper/2603.21908/) (2026)
- [YOLO Object Detectors for Robotics -- a Comparative Study](https://mlsanity.com/paper/2603.27029/) (2026)

## Abstract (arXiv)

Passive cooling eliminates the energy overhead and mechanical failure modes of fans, making it attractive for edge deployment, yet sustained Deep Neural Network (DNN) inference on passively cooled edge Systems-on-Chip (SoCs) is bottlenecked by thermal throttling. To address this, we propose an empirically calibrated, state-aware Dynamic Voltage and Frequency Scaling (DVFS) scheduler. Unlike heuristic-driven controllers, our methodology utilizes time-domain guards and absolute temperature bounds, with derivative triggers acting as safeguards against sharp thermal spikes. Evaluated on a passively cooled Raspberry Pi 5 running YOLOv8n, our scheduler eliminates all observed thermal throttling events during sustained 30-minute workloads. It outperforms a temperature-only reactive baseline by achieving a 6.8% higher frame rate (Cohen's d = 8.73) while consuming 1.9% less energy per frame. Furthermore, our optimized passive scheduling surpasses an actively cooled reference system in energy efficiency (Joules/frame), though active cooling remains superior for raw throughput. Through isolated ablations, we show that the dwell guard is necessary for run-to-run reproducibility. Finally, exploratory boundary probes indicate that the passive operating envelope closes at ambient temperatures (≥ 27^circC) where nonlinear leakage defeats DVFS-based control. These results indicate that, within the mapped envelope, correct scheduling can make mechanical cooling unnecessary for sustained edge inference on this platform.