Impact of Thermal Throttling on Long-Term Visual Inference in a CPU-based Edge Device

TL;DR

This study investigates how thermal throttling affects long-term visual inference performance on Raspberry Pi 4B, highlighting the benefits of active cooling and the impact of ambient temperature on throughput.

Contribution

It provides a comprehensive analysis of thermal throttling effects on CNN inference on edge devices, emphasizing active cooling's role and ambient temperature influence.

Findings

Active cooling prevents thermal throttling, increasing throughput by up to 90%.

Fan usage varies between 33% and 65%, affecting power consumption.

Ambient temperature significantly impacts system throughput without active cooling.

Abstract

Many application scenarios of edge visual inference, e.g., robotics or environmental monitoring, eventually require long periods of continuous operation. In such periods, the processor temperature plays a critical role to keep a prescribed frame rate. Particularly, the heavy computational load of convolutional neural networks (CNNs) may lead to thermal throttling and hence performance degradation in few seconds. In this paper, we report and analyze the long-term performance of 80 different cases resulting from running 5 CNN models on 4 software frameworks and 2 operating systems without and with active cooling. This comprehensive study was conducted on a low-cost edge platform, namely Raspberry Pi 4B (RPi4B), under stable indoor conditions. The results show that hysteresis-based active cooling prevented thermal throttling in all cases, thereby improving the throughput up to approximately 90% versus no cooling. Interestingly, the range of fan usage during active cooling varied from 33% to 65%. Given the impact of the fan on the power consumption of the system as a whole, these results stress the importance of a suitable selection of CNN model and software components. To assess the performance in outdoor applications, we integrated an external temperature sensor with the RPi4B and conducted a set of experiments with no active cooling in a wide interval of ambient temperature, ranging from 22 {\deg}C to 36 {\deg}C. Variations up to 27.7% were measured with respect to the maximum throughput achieved in that interval. This demonstrates that ambient temperature is a critical parameter in case active cooling cannot be applied.