CarbonCP: Carbon-Aware DNN Partitioning with Conformal Prediction for Sustainable Edge Intelligence

TL;DR

CarbonCP is a novel framework that optimizes DNN partitioning in edge computing to significantly reduce carbon emissions while maintaining low latency and battery use, using conformal prediction for uncertainty management.

Contribution

This work introduces CarbonCP, a context-adaptive, carbon-aware DNN partitioning method leveraging conformal prediction to balance emissions, latency, and battery consumption in edge systems.

Findings

Reduces operational carbon emissions by up to 58.8%.

Maintains a 9.9% error rate in predictions.

Balances system performance with environmental impact.

Abstract

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.