基于经验校准DVFS的可持续边缘视觉：消除被动冷却硬件上的热节流
Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled Hardware
浏览论文内容
中文总结 AI 辅助
针对被动冷却边缘SoC上DNN推理的热节流瓶颈，提出经经验校准的状态感知DVFS调度器，在树莓派5上实现无热节流，能效优于主动冷却系统，帧率与可复现性均达标。
中文摘要 AI 辅助
被动冷却消除了风扇的能量开销和机械故障模式，使其在边缘部署中颇具吸引力，但在被动冷却的边缘片上系统（SoC）上持续运行深度神经网络（DNN）推理会受到热节流的瓶颈。为解决该问题，我们提出一种经经验校准的、感知状态的动态电压频率调节（DVFS）调度器。与启发式驱动的控制器不同，我们的方法采用时域阈值和绝对温度边界，导数触发器作为应对急剧热峰值的保障措施。在运行YOLOv8n的被动冷却树莓派5（Raspberry Pi 5）上进行评估，我们的调度器在持续30分钟的工作负载期间消除了所有观测到的热节流事件。它比仅基于温度的反应式基准表现更优，帧率提升6.8%（Cohen's d=8.73），且每帧能耗降低1.9%。此外，我们优化的被动调度在能效（焦耳/帧）上优于主动冷却参考系统，尽管主动冷却在原始吞吐量上仍更出色。通过单独的消融实验，我们证明驻留阈值是实现运行间可复现性的必要条件。最后，探索性边界探测表明，被动工作范围在环境温度（≥27℃）下闭合，此时非线性泄漏会破坏基于DVFS的控制。这些结果表明，在已测绘的工作范围内，正确的调度可使该平台上的持续边缘推理无需机械冷却。
英文摘要
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 ($\ge 27^\circ$C) 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.
发表机构
- University of Southern Mississippi（南密西西比大学）
机构由 AI 辅助整理，请以论文原文为准。
