Impact of Thermal Throttling on Long-Term Visual Inference in a CPU-Based Edge Device
Open Access
- 10 December 2020
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 9 (12) , 2106
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 five CNN models on four software frameworks and two 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 °C to 36 °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.Keywords
All Related Versions
Funding Information
- European Union H2020 MSCA (765866)
- Office of Naval Research (N00014-19-1-2156)
- Spanish Government MICINN (European Region Development Fund, ERDF/FEDER) (RTI2018-097088-B-C31)
This publication has 15 references indexed in Scilit:
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
- Benchmark Analysis of Representative Deep Neural Network ArchitecturesIEEE Access, 2018
- A Survey on Internet of Things: Architecture, Enabling Technologies, Security and Privacy, and ApplicationsIEEE Internet of Things Journal, 2017
- An Adaptive and Integrated Low-Power Framework for Multicore Mobile ComputingMobile Information Systems, 2017
- Deep Residual Learning for Image Recognition2016
- Going deeper with convolutions2015
- Deep learningNature, 2015
- Early forest fire detection by vision-enabled wireless sensor networksInternational Journal of Wildland Fire, 2012
- ImageNet: A large-scale hierarchical image database2009