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 modeling tool for precise carbon footprint estimation in IoT-enabled DL, demonstrating a maximum $\pm21\%$ deviation in carbon footprint values compared to actual measurements across various DL models. Additionally, practical applications of \carb are showcased through multiple user case studies.

翻译：为提升隐私保护并保障服务质量（QoS），深度学习（DL）模型日益部署于物联网设备上进行数据处理，这显著增加了物联网环境下深度学习相关的碳足迹——涵盖运行阶段与隐含阶段两个维度。现有运行能耗预测工具往往忽略量化深度学习模型及新兴神经处理单元（NPU），而隐含碳足迹建模工具则忽视物联网设备中常见的非计算硬件组件，导致面向物联网赋能的深度学习碳足迹精准建模工具存在空白。本文提出\textit{\carb}这一端到端建模工具，用于物联网赋能深度学习的精确碳足迹估算，在多种深度学习模型上，其碳足迹值相比实际测量值的偏差最大为$\pm21\%$。此外，通过多项用户案例研究展示了\carb的实用价值。