arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.15824cs.LGcs.AI
收藏

碳强度感知的DNN自适应推理

Carbon Intensity-Aware Adaptive Inference of DNNs

Singapore American School(新加坡美国学校)

Jiwan Jung

AI总结:

针对DNN推理高能耗与碳足迹问题,提出随日间碳强度变化自适应调整模型大小与精度的启发式算法,并引入碳排放效率指标,在提升视觉识别精度时实现高达80%的碳排放效率提升。

摘要:

DNN推理因显著的能耗和由此产生的高碳足迹而闻名,通过在一天中随碳强度变化调整模型大小和精度,可使其更具可持续性。我们的启发式算法在低碳强度时期使用较大、高精度的模型,在高碳强度时期使用较小、低精度的模型。我们还引入了碳排放效率指标,定量衡量自适应模型选择在碳足迹方面的有效性。评估表明,所提方法在提升视觉识别服务精度时,可将碳排放效率提高多达80%。

英文摘要:

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%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑