Carbon Intensity-Aware Adaptive Inference of DNNs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Jung, Jiwan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909148106457088
author Jung, Jiwan
author_facet Jung, Jiwan
contents 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%.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15824
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Carbon Intensity-Aware Adaptive Inference of DNNs
Jung, Jiwan
Machine Learning
Artificial Intelligence
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%.
title Carbon Intensity-Aware Adaptive Inference of DNNs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2403.15824