Investigating hardware and software aspects in the energy consumption of machine learning: A green AI‐centric analysis

计算机科学 x86个 能源消耗 软件 机器学习 人工智能 推论 随机森林 硬件体系结构 能量(信号处理) 高效能源利用 计算机工程 嵌入式系统 操作系统 工程类 电气工程 统计 数学
作者
André Yokoyama,Mariza Ferro,Felipe B. de Paula,Vitor G. Vieira,Bruno Schulze
出处
期刊:Concurrency and Computation: Practice and Experience [Wiley]
卷期号:35 (24) 被引量:5
标识
DOI:10.1002/cpe.7825
摘要

Summary Much has been discussed about artificial intelligence's negative environmental impacts due to its power‐hungry Machine Learning algorithms and emissions linked to this. This work discusses three direct impacts of AI on energy consumption associated with computation: the software, the hardware, and the energy source's carbon intensity. We present an up‐to‐date revision of the literature and assess it through experiments. For hardware, we evaluate the use of ARM‐based single‐board computers for training Machine Learning algorithms. An experimental setup was developed training the algorithm XGBoost and its cost‐effectiveness (energy consumption, acquisition cost, and execution time) compared with the X86‐64 and GPU architectures and other algorithms. In addition, the is estimated for these experiments and compared for three energy sources. The results show that this type of architecture can become a viable and greener alternative, not only for inference but also for training these algorithms. Finally, we evaluated low precision for training Random Forest algorithms with different datasets for the software aspect. Results show that is possible energy reduction with no decrease in accuracy.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
wss发布了新的文献求助10
1秒前
生动谷蓝完成签到,获得积分10
1秒前
文献文献完成签到 ,获得积分10
1秒前
plummin发布了新的文献求助10
3秒前
乐乐应助科研虫采纳,获得30
3秒前
搜集达人应助科研通管家采纳,获得10
3秒前
zhang2023发布了新的文献求助10
3秒前
NexusExplorer应助科研通管家采纳,获得10
3秒前
共享精神应助科研通管家采纳,获得10
3秒前
Jasper应助科研通管家采纳,获得10
4秒前
ezio完成签到 ,获得积分0
4秒前
科研通AI2S应助科研通管家采纳,获得10
4秒前
Kyo应助科研通管家采纳,获得10
4秒前
完美世界应助科研通管家采纳,获得10
4秒前
李爱国应助科研通管家采纳,获得10
4秒前
科研通AI2S应助科研通管家采纳,获得10
4秒前
5秒前
科研通AI2S应助科研通管家采纳,获得10
5秒前
赘婿应助科研通管家采纳,获得10
5秒前
5秒前
wanci应助科研通管家采纳,获得10
5秒前
科研通AI2S应助科研通管家采纳,获得10
5秒前
酷波er应助科研通管家采纳,获得10
6秒前
6秒前
6秒前
6秒前
WallfacerCN应助科研通管家采纳,获得50
6秒前
6秒前
6秒前
czx完成签到,获得积分10
8秒前
9秒前
9秒前
10秒前
chen发布了新的文献求助10
13秒前
沉默的红牛完成签到 ,获得积分10
13秒前
13秒前
情怀应助沐阳d采纳,获得10
14秒前
Hello应助wss采纳,获得10
14秒前
愉快若剑发布了新的文献求助10
15秒前
sunflowers完成签到 ,获得积分10
17秒前
高分求助中
TM 5-855-1(Fundamentals of protective design for conventional weapons) 1000
Threaded Harmony: A Sustainable Approach to Fashion 799
草地生态学 500
Retention of title in secured transactions law from a creditor's perspective: A comparative analysis of selected (non-)functional approaches 500
"Sixth plenary session of the Eighth Central Committee of the Communist Party of China" 400
Introduction to Modern Controls, with illustrations in MATLAB and Python 310
PROJECT STUDIES; -A LATE MODERN UNIVERSITY REFORM? 300
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3057772
求助须知:如何正确求助?哪些是违规求助? 2714072
关于积分的说明 7439066
捐赠科研通 2359232
什么是DOI,文献DOI怎么找? 1249940
科研通“疑难数据库(出版商)”最低求助积分说明 607315
版权声明 596334