Deep learning applications at the network edge lead to a significant growth in AI-related carbon emissions, presenting a critical sustainability challenge. The existing edge computing frameworks optimize for latency and throughput, but they largely ignore the environmental impact of inference workloads. This paper introduces CarbonEdge, a carbon-aware deep learning inference framework that extends adaptive model partitioning with carbon footprint estimation and green scheduling apabilities. We propose a carbon-aware scheduling algorithm that extends traditional weighted scoring with a carbon efficiency metric, supporting a tunable performance--carbon trade-off (demonstrated via weight sweep). Experimental evaluations on Docker-simulated heterogeneous edge environments show that CarbonEdge-Green mode achieves a 22.9% reduction in carbon emissions compared to monolithic execution. The framework achieves 1.3x improvement in carbon efficiency (245.8 vs 189.5 inferences per gram CO2) with negligible scheduling overhead (0.03ms per task). These results highlight the framework's potential for sustainable edge AI deployment, providing researchers and practitioners a tool to quantify and minimize the environmental footprint of distributed deep learning inference.

翻译：网络边缘的深度学习应用导致与人工智能相关的碳排放显著增长，带来了严峻的可持续性挑战。现有的边缘计算框架针对延迟和吞吐量进行优化，但很大程度上忽略了推理工作负载对环境的影响。本文介绍了CarbonEdge，一个碳感知深度学习推理框架，该框架通过碳足迹估算和绿色调度能力扩展了自适应模型划分。我们提出了一种碳感知调度算法，该算法将传统加权评分与碳效率指标相结合，支持可调的性能-碳权衡（通过权重扫描验证）。在Docker模拟的异构边缘环境下的实验评估表明，与整体执行相比，CarbonEdge绿色模式实现了22.9%的碳排放减少。该框架在碳效率方面提升了1.3倍（每克CO2推理次数从189.5提升至245.8），且调度开销可忽略不计（每个任务0.03毫秒）。这些结果凸显了该框架在可持续边缘AI部署方面的潜力，为研究人员和从业者提供了一个量化并最小化分布式深度学习推理环境足迹的工具。