Estimating the Power Consumption of Heterogeneous Devices when performing AI Inference
This work addresses power efficiency for IoT devices running AI inference, but it is incremental as it applies existing methods to new hardware data.
The paper tackled the problem of understanding power consumption versus performance for IoT devices performing computer vision tasks, specifically by analyzing the NVIDIA Jetson Nano board during object classification with YOLOv5 models, resulting in YOLOv5n achieving 12.34 fps and 0.154 mWh/frame.
Modern-day life is driven by electronic devices connected to the internet. The emerging research field of the Internet-of-Things (IoT) has become popular, just as there has been a steady increase in the number of connected devices. Since many of these devices are utilised to perform CV tasks, it is essential to understand their power consumption against performance. We report the power consumption profile and analysis of the NVIDIA Jetson Nano board while performing object classification. The authors present an extensive analysis regarding power consumption per frame and the output in frames per second using YOLOv5 models. The results show that the YOLOv5n outperforms other YOLOV5 variants in terms of throughput (i.e. 12.34 fps) and low power consumption (i.e. 0.154 mWh/frame).