Get Started
Home
Topics
Search
Library
Research questionHow can passively cooled edge devices sustain DNN inference under thermal constraints?Sustained DNN workloads can heat passively cooled devices until thermal safeguards lower their operating frequency and inference throughput. Thermal control must therefore limit heat without making sustained inference impractically slow or energy intensive.
AI
Computer Vision
Inference Optimization
Small / On-device Models
Technology
Latest papersRecent research connected to this question, newest first.Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled HardwareThe source tests an empirically calibrated dynamic voltage and frequency controller on a passively cooled Raspberry Pi 5 running YOLOv8n during sustained workloads and probes its ambient-temperature operating boundary. Evidence is specific to that platform, workload, duration, and tested thermal envelope; active cooling remains relevant when maximum throughput is the priority.research paper · Sep 4, 2026
Related questions
How can edge analog in-memory inference reduce energy while certifying errors from heterogeneous, imperfect accelerators?How can CNN inference fit on bare-metal microcontrollers with severe memory, binary-size, and runtime limits?How can complex neural-network graphs be mapped across heterogeneous SoCs to balance inference latency and throughput?How can on-device LLM inference overlap weight I/O and computation under tight DRAM without stale sparsity decisions?