IoTCO2: Assessing the End-To-End Carbon Footprint of Internet-of-Things-Enabled Deep Learning
This addresses the need for precise carbon footprint estimation in IoT-enabled deep learning, which is crucial for sustainability efforts in this domain, though it is incremental as it builds on existing modeling approaches.
The paper tackles the problem of accurately assessing the carbon footprint of deep learning on IoT devices, which is often overlooked in existing tools, and introduces a tool called IoTCO2 that achieves deviations as low as 5% for operational and 3.23% for embodied carbon footprints compared to actual measurements.
To improve privacy and ensure quality-of-service (QoS), deep learning (DL) models are increasingly deployed on Internet of Things (IoT) devices for data processing, significantly increasing the carbon footprint associated with DL on IoT, covering both operational and embodied aspects. Existing operational energy predictors often overlook quantized DL models and emerging neural processing units (NPUs), while embodied carbon footprint modeling tools neglect non-computing hardware components common in IoT devices, creating a gap in accurate carbon footprint modeling tools for IoT-enabled DL. This paper introduces \textit{\carb}, an end-to-end tool for precise carbon footprint estimation in IoT-enabled DL, with deviations as low as 5\% for operational and 3.23\% for embodied carbon footprints compared to actual measurements across various DL models. Additionally, practical applications of \carb~are showcased through multiple user case studies.