CarbonCP: Carbon-Aware DNN Partitioning with Conformal Prediction for Sustainable Edge Intelligence
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.
- The real climate and transformative impact of ICT: A critique of estimates, trends, and regulations. Patterns, 2(9):100340, 2021.
- Sustainable AI: Environmental implications, challenges and opportunities. In Proc. Machine Learning and Systems (MLSys), volume 4, pages 795–813, 2022.
- Measuring the algorithmic efficiency of neural networks. arXiv preprint arXiv:2005.04305, 2020.
- A tutorial on conformal prediction. Journal of Machine Learning Research, 9(3), 2008.
- Dynamic adaptive dnn surgery for inference acceleration on the edge. In IEEE Conference on Computer Communications (INFOCOM), pages 1423–1431, 2019.
- Edge ai: On-demand accelerating deep neural network inference via edge computing. IEEE Transactions on Wireless Communications, 19(1):447–457, 2019.
- Jointdnn: An efficient training and inference engine for intelligent mobile cloud computing services. IEEE Transactions on Mobile Computing, 20(2):565–576, 2019.
- Electricity Maps. Reduce carbon emissions with actionable electricity data. accessed on Mar. 2024.
- Neurosurgeon: Collaborative intelligence between the cloud and mobile edge. ACM SIGARCH Computer Architecture News, 45(1):615–629, 2017.
- An adaptive DNN inference acceleration framework with end–edge–cloud collaborative computing. Future Generation Computer Systems, 140:422–435, 2023.
- Bottlenet: A deep learning architecture for intelligent mobile cloud computing services. In 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), pages 1–6, 2019.
- Algorithmic learning in a random world, volume 29. Springer.
- Conformal prediction under covariate shift. Advances in neural information processing systems, 32, 2019.
- Distribution-free predictive inference for regression. Journal of the American Statistical Association, 113(523):1094–1111, 2018.
- Edge intelligence: On-demand deep learning model co-inference with device-edge synergy. In Proc. the 2018 Workshop on Mobile Edge Communications, pages 31–36, 2018.
- Jalad: Joint accuracy-and latency-aware deep structure decoupling for edge-cloud execution. In 2018 IEEE 24th International Conference on Parallel and Distributed systems (ICPADS), pages 671–678, 2018.
- Timothy John Sullivan. Introduction to uncertainty quantification, volume 63. Springer, 2015.
- Christian Soize. Uncertainty quantification. Springer, 2017.
- Weight uncertainty in neural network. In International Conference on Machine Learning, pages 1613–1622. PMLR, 2015.
- Radford M Neal. Bayesian learning for neural networks, volume 118. Springer Science & Business Media, 2012.
- Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning, pages 1050–1059. PMLR, 2016.
- Pitfalls of in-domain uncertainty estimation and ensembling in deep learning. arXiv preprint arXiv:2002.06470, 2020.
- Simple and scalable predictive uncertainty estimation using deep ensembles. In Proc. the 31st International Conference on Neural Information Processing Systems (NIPS), page 6405–6416, 2017.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.