This paper presents a solution to address carbon emission mitigation for end-to-end edge computing systems, including the computing at battery-powered edge devices and servers, as well as the communications between them. We design and implement, CarbonCP, a context-adaptive, carbon-aware, and uncertainty-aware AI inference framework built upon conformal prediction theory, which balances operational carbon emissions, end-to-end latency, and battery consumption of edge devices through DNN partitioning under varying system processing contexts and carbon intensity. Our experimental results demonstrate that CarbonCP is effective in substantially reducing operational carbon emissions, up to 58.8%, while maintaining key user-centric performance metrics with only 9.9% error rate.

翻译：摘要：本文提出了一种解决方案，用于减少端到端边缘计算系统的碳排放，涵盖电池供电的边缘设备与服务器端的计算过程以及两者间的通信。我们设计并实现了CarbonCP——一种基于共形预测理论、具备上下文自适应、碳感知和不确定性感知能力的AI推理框架。该框架通过在不同系统处理上下文与碳强度条件下对深度神经网络（DNN）进行分区，有效平衡了运营碳排放、端到端延迟及边缘设备的电池消耗。实验结果表明，CarbonCP能够显著降低运营碳排放，降幅高达58.8%，同时仅以9.9%的误差率维持关键的用户中心性能指标。