Research on intelligent computing power prediction based on AI large models

LI Shuangjie; DU Chunxiang; XIAO Ziyu

doi:10.11959/j.issn.1000-0801.2024215

您当前的位置：

首页 >

文章列表页 >

Research on intelligent computing power prediction based on AI large models

Engineering and Application | 更新时间：2024-12-02

- Research on intelligent computing power prediction based on AI large models
- Telecommunications Science Vol. 40, Issue 10, Pages: 144-151(2024)
- 作者机构：
  
  中国移动通信集团设计院有限公司，北京 100080
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2024215
  CLC： TP301
- Received：21 June 2024，
  
  Revised：11 September 2024，
  
  Published：20 October 2024
- 稿件说明：
移动端阅览
李双杰,杜春香,肖子玉.人工智能大模型发展带来的智能算力需求测算研究[J].电信科学,2024,40(10):144-151.

LI Shuangjie,DU Chunxiang,XIAO Ziyu.Research on intelligent computing power prediction based on AI large models[J].Telecommunications Science,2024,40(10):144-151.
李双杰,杜春香,肖子玉.人工智能大模型发展带来的智能算力需求测算研究[J].电信科学,2024,40(10):144-151. DOI： 10.11959/j.issn.1000-0801.2024215.

LI Shuangjie,DU Chunxiang,XIAO Ziyu.Research on intelligent computing power prediction based on AI large models[J].Telecommunications Science,2024,40(10):144-151. DOI： 10.11959/j.issn.1000-0801.2024215.

摘要

以ChatGPT为代表的人工智能大模型的爆发带动智能算力需求快速增长，电信运营商、云服务商等纷纷加大智算中心布局，大模型的发展对智能算力有多大规模需求、对智算中心的布局与建设有着十分重要的影响。从大模型对智能算力的消耗特点出发，对影响大模型算力消耗的关键影响因素进行深入分析，并基于不同参数量级不同行业类型构建了分层次分阶段的大模型智能算力需求测算模型，对大模型对智能算力的需求进行系统分析，为智算中心的建设提供明确的业务输入与支撑。

Abstract

AI large models

represented by ChatGPT

have driven a rapid growth in intelligent computing power demand. Telecom operators and cloud service providers are increasingly expanding their intelligent computing center layouts. The future trends of large models and the scale of their computing power demand are of great importance for the layout and construction of intelligent computing centers. Starting from the consumption characteristics of computing power by AI large models

the key influencing factors of computing power consumption were analyzed. Based on multi-level models with different parameter scales and industry types

the intelligent computing power demand of AI large models was systematically analyzed

providing clear business inputs and support for the construction of intelligent computing centers.

关键词

Keywords

references

李正茂 , 雷波 , 孙震强 , 等 . 云网融合: 算力时代的数字信息 . 基础设施 [M ] . 北京 : 中信出版社 , 2022 .

LI Z M , LEI B , SUN Z Q , et al . Cloud network convergence: computing era’s digital information infrastructure [M ] . Beijing : CITIC Press Group , 2022 .

IDC . 2022-2023全球计算力发展指数评估报告 [R ] . 2023 .

IDC . 2022-2023 global computing index [R ] . 2023 .

中国信息通信研究院 . 中国算力发展指数白皮书 [R ] . 2021 .

CAICT . White paper on China’s computing index [R ] . 2021 .

孙长秋 , 杜长斌 , 李菲 , 等 . 人工智能及大模型技术研究 [J ] . 通信管理与技术 , 2024 ( 3 ): 43 - 47 .

SUN C Q , DU C B , LI F , et al . Research on artificial intelligence and large model technology [J ] . Communications Management and Technology , 2024 ( 3 ): 43 - 47 .

中国信息通信研究院 . 中国算力发展指数白皮书（2023年） [R ] . 2023 .

CAICT . White paper on China’s computing index(2023) [R ] . 2023 .

KAPLAN J , MCCANDLISH S , HENIGHAN T , et al . Scaling laws for neural language models [J ] . 2020 , arXiv. 2001 . 08361 .

WEI J , TAY Y , BOMMASANI R , et al . Emergent abilities of large language models [J ] . 2022 , arXiv: 2206.07682 .

李国杰 . 大数据与计算模型 [J ] . 大数据 , 2024 , 10 ( 1 ) : 9 - 16 .

LI G J . Big data and computing models [J ] . Big Data Research , 2024 , 10 ( 1 ) : 9 - 16 .

孙柏林 . 大模型评述 [J ] . 计算机仿真 , 2024 , 41 ( 1 ): 1 - 7,24 .

SUN B L . Review of large models [J ] . Computer Simulation , 2024 , 41 ( 1 ): 1 - 7,24 .

田海东 , 张明政 , 常锐，等 . 大模型训练技术综述 [J ] . 中兴通讯技术 , 2024 ( 8 ): 21 - 28 .

TIAN H D , ZHANG M Z , CHANG R , et al . A survey on large model training technologies [J ] . ZTE Technology Journal , 2024 ( 8 ): 21 - 28 .

严昊 , 刘禹良 , 金连文，等 . 类ChatGPT大模型发展、应用与前景 [J ] . 中国图象图形学报 , 2023 , 28 ( 9 ) : 2749 - 2762 .

YAN H , LIU Y L , JIN L W , et al . The development, application, and future of LLM similar to ChatGPT [J ] . Journal of Image and Graphics , 2023 , 28 ( 9 ) : 2749 - 2762 .

温小振 , 常金凤 , 吴美希 . 综合算力发展现状与趋势分析 [J ] . 信息通信技术与政策 , 2024 , 50 ( 2 ) : 7 - 11 .

WEN X Z , CHANG J F , WU M X . Analysis of current situation and trend of comprehensive computing power development [J ] . Information and Communications Technology and Policy , 2024 , 50 ( 2 ): 7 - 11 .

王月 , 盛凯 , 常金凤，等 . 数据中心基础设施关键技术应用及发展 [J ] . 信息通信技术与政策 , 2021 , 47 ( 4 ) : 27 - 31 .

WANG Y , SHENG K , CHANG J F , et al . Application and development of key technologies in data center infrastructure [J ] . Information and Communications Technology and Policy , 2021 , 47 ( 4 ) : 27 - 31 .

殷凯凯 . 基于电信运营商视角的智算中心规划建设关键要点分析及建议 [J ] . 现代信息科技 , 2024 , 8 ( 1 ) : 22 - 27 .

YIN K K . Analysis and suggestions of key points for planning and construction of artificial intelligence computing center based on telecom operators' perspectives [J ] . Modern Informationn Technology , 2024 , 8 ( 1 ) : 22 - 27 .

李正茂 , 王桂荣 . 论算力时代的三定律 [J ] . 电信科学 , 2022 , 38 ( 6 ): 13 - 17 .

LI Z M , WANG G R . Laws of computing power in the computing power era [J ] . Telecommunications Science , 2022 , 38 ( 6 ) : 13 - 17 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰