DNN inference, known for its significant energy consumption and the resulting high carbon footprint, can be made more sustainable by adapting model size and accuracy to the varying carbon intensity throughout the day. Our heuristic algorithm uses larger, high-accuracy models during low-intensity periods and smaller, lower-accuracy ones during high-intensity periods. We also introduce a metric, carbon-emission efficiency, which quantitatively measures the efficacy of adaptive model selection in terms of carbon footprint. The evaluation showed that the proposed approach could improve the carbon emission efficiency in improving the accuracy of vision recognition services by up to 80%.
Measuring the Carbon Intensity of AI in Cloud Instances
Allen Institute for AI(艾伦人工智能研究所);University of Washington(华盛顿大学);Microsoft Research Montreal(微软蒙特利尔研究院);Microsoft(微软公司);Hebrew University of Jerusalem(希伯来大学);Carnegie Mellon University(卡内基梅隆大学);Hugging Face(抱抱脸)
Stable Time Series Prediction of Enterprise Carbon Emissions Based on Causal Inference
School of Economics and Management, China University of Geosciences (Beijing)(经济管理学院,中国地质大学(北京));MOE Laboratory of Philosophy and Social Sciences for Mineral Resources Security Governance, China University of Geosciences (Beijing)(矿产资源安全保障治理哲学社会科学教育部重点实验室,中国地质大学(北京))
MAIZX: A Carbon-Aware Framework for Optimizing Cloud Computing Emissions
KTH Royal Institute of Technology(皇家理工学院);Norwegian University of Science and Technology(挪威科学与技术大学);Simula Metropolitan Centre for Digital Engineering(Simula 城市数字工程中心)
Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling
Inria Centre at Université Côte d’Azur(法国国家信息与自动化技术研究院(Inria)亚维农分校);Accenture(埃森哲);Department of Electrical Engineering (ISY), Linköping University(利厄普大学电气工程系)