The national computing power network driven by intelligent collaboration: research on architectural evolution, implementation bottlenecks, and optimization pathways

doi:10.12267/j.issn.2096-5931.2025.10.004

Abstract

Abstract:

This paper systematically investigates the core mechanisms by which artificial intelligence technology empowers a national integrated computing network, set against the backdrop of China’s “Eastern Data, Western Computing” strategic initiative. Drawing upon practical experiences from this national project, the study analyzes the current development status and critical bottlenecks of computing networks, focusing on dimensions such as scheduling efficiency and resource integration. Concurrently, through an in-depth examination of cases, including the “China Computing Network” at Pengcheng Laboratory, this paper proposes optimized pathways for intelligent collaborative scheduling in computing networks, providing theoretical foundations for the construction of an efficient, secure, and intelligent integrated computing network.

Key words: computing network, scheduling efficiency, AI-infra, eastern data western computing, optimization pathways

CLC Number:

TN929.12

LI Ruochen, WEN Xinbo, DU Jingru, LI Shiyu, XIE Guangfen, DONG Yichuan. The national computing power network driven by intelligent collaboration: research on architectural evolution, implementation bottlenecks, and optimization pathways[J]. Information and Communications Technology and Policy, 2025, 51(10): 23-30.

Add to citation manager EndNote|Ris|BibTeX

URL:

http://ictp.caict.ac.cn/EN/10.12267/j.issn.2096-5931.2025.10.004

http://ictp.caict.ac.cn/EN/Y2025/V51/I10/23

References 35

[1]	裴培, 吴鹏, 吕城锦, 等. 全国一体化算力网探索与研究[J]. 通信世界, 2025(7):36-41.
[2]	王思航, 匡先辉, 郭煜, 等. 加快构建全国一体化算力网分析[J]. 决策咨询, 2025(2):12-13,41.
[3]	孔思淇, 潘泽友, 路海, 等. ESnet架构、建设进展及其与CSTnet的比较[J]. 计算机技术与发展, 2011, 21(12):18-21,25.
[4]	ESnet. High energy physics network requirements review final report[R], 2020.
[5]	ESnet. ESnet launches next-generation network to enhance collaborative science[EB/OL]. (2022-10-11)[2025-09-15]. https://www.es.net/news-and-publications/esnet-news/2022/esnet-launches-next-generation-network-to-enhance-collaborative-science/.
[6]	Lawrence Berkeley National Laboratory. ESnet turns on 400G circuits, supercharging multi-site scientific research[EB/OL]. (2023-10-25)[2025-09-15]. https://newscenter.lbl.gov/2023/10/25/esnet-turns-on-400g-circuits-supercharging-multi-site-scientific-research/.
[7]	安捷, 刘莹, 任罡, 等. 世界各国教科网建设(四)[J]. 中国教育网络, 2015(8):40-43.
[8]	WANG W, XIE R, TANG Q, et al. Service anycast forwarding for software defined computing power network[C]// 2025 IEEE Wireless Communications and Networking Conference(WCNC). Milan: IEEE, 2025:1-6.
[9]	梁芳, 佟恬, 马贺荣, 等. 东数西算下算力网络发展分析[J]. 信息通信技术与政策, 2022, 48(11):79-83. doi: 10.12267/j.issn.2096-5931.2022.11.010
[10]	梅建平. 以推进中国算力网建设发展新质生产力[J]. 中国网信, 2025(9):32-35.
[11]	刘芹, 刘鹏, 武振宇, 等. 东数西算战略下运营商业务西迁部署研究[J]. 电信工程技术与标准化, 2024, 37(7):55-61.
[12]	傅文军, 钱军波, 毛雄飞, 等. 东数西算之算力网络试点建设探讨[J]. 中国仪器仪表, 2022(3):17-21.
[13]	郭亮. 专题导读:算力网络[J]. 信息通信技术与政策, 2025, 51(2):1.
[14]	归律, 王悦, 张钟琴. 东数西算中多云管理技术应用浅析[J]. 信息通信技术与政策, 2022, 48(11):84-92. doi: 10.12267/j.issn.2096-5931.2022.11.011
[15]	栗蔚, 王雨萌, 立言, 等. “东数西算”背景下算力服务对算力经济发展影响分析[J]. 数据与计算发展前沿, 2022, 4(6):13-19.
[16]	梁腾, 杨健, 杨佳宇, 等. 广域长距离高性能传输技术研究与讨论[J]. 科技导报, 2025, 43(9):31-37. doi: 10.3981/j.issn.1000-7857.2024.08.01032
[17]	高文. 中国算力网的机遇与挑战[J]. 中国计算机学会通讯, 2023, 19(1):31-36.
[18]	李佳颖, 杨泽民, 宋哲代, 等. Kubernetes容器云的弹性伸缩方法[J]. 电子科技, 2025, 38(3):32-39.
[19]	李为丽. 可解释的云平台任务终止状态预测方法研究[D]. 新乡: 河南师范大学, 2023.
[20]	柯尊旺. Mesos平台下多资源调度算法的研究与改进[D]. 乌鲁木齐: 新疆大学, 2016.
[21]	王荣丽, 侯秀萍. 基于优先级权重的HadoopYARN调度算法[J]. 吉林大学学报(信息科学版), 2017, 35(4):443-448.
[22]	CHOUDHARY A. Google cluster data centers[M]// Fifth Congresson Intelligent Systems: CIS 2024. London: Springer Nature, 2025, 1276:127.
[23]	SARKAR A, RAGAVAN S, WILLIAMS J, et al. End-user encounters with lambda abstraction in spreadsheets:Apollo’s bow or Achilles’ heel?[C]// 2022 IEEE Symposium on Visual Languages and Human-Centric Computing(VL/HCC). Roma: IEEE, 2022:1-11.
[24]	OpenI启智社区. 不忘初心·砥砺前行:OpenI启智社区2024年度回顾[EB/OL]. (2025-01-22)[2025-09-15]. https://mp.weixin.qq.com/s/AIAGnAcXBrBL-U9rt7J0t9w.
[25]	LUO J, PADURARU C, VOICU O, et al. Controlling commercial cooling systems using reinforcement learning[J]. arXiv Preprint, arXiv:2211.07357, 2022.
[26]	SALAMI B, PARASYRIS K, CRISTAL A, et al. LEGaTO: low-energy, secure, and resilient toolset for heterogeneous computing[J]. arXiv Preprint,arXiv:1912.01563, 2019.
[27]	杨金涛. 偏好多目标强化学习算法及其在路径规划中的应用[D]. 南京: 东南大学, 2023.
[28]	ESMAILI A, PEDRAM M. Energy-aware scheduling of jobs in heterogeneous cluster systems using deep reinforcement learning[C]// 2020 21st International Symposium on Quality Electronic Design (ISQED), Santa Clara:IEEE, 2020:426-431.
[29]	SOUZA A, JASORIA S, CHAKRABARTY B, et al. CASPER:carbon-aware scheduling and provisioning for distributed web services[C]// IGSC’23: the 14th International Green and Sustainable Computing Conference. New York: Association for Computing Machinery. 2023:67-73.
[30]	D'ANTONIO L, TEHERAN J. Computing node scanning tool for collaborative science[R], 2021.
[31]	BRAUD A, FROMENTOUX G, RADIER B, et al. The road to European digital sovereignty with Gaia-X and IDSA[J]. IEEE network, 2021, 35(2):4-5.
[32]	PREMKUMAR V, BHANDARI V. Ultra-Low latency video streaming using verizon 5G and AWS wavelength[J]. International Journal of Management IT and Engineering, 2021, 11(5):29-33.
[33]	KOVAČ M, NOTTON P, HOFMAN D, et al. How Europe is preparing its core solution for exascale machines and a global, sovereign, advanced computing platform[J]. Mathematical and Computational Applications, 2020, 25(3):46.
[34]	张叶红, 董一川, 相洋, 等. 从“算力中心”到“算力网”:从算力角度谈算网一体的机遇与挑战[J]. 信息通信技术, 2023, 17(3):28-33.
[35]	张政, 冯少飞. 大模型算力基础设施技术趋势、关键挑战与发展路径[J]. 信息通信技术与政策, 2024, 50(6):2-9. doi: 10.12267/j.issn.2096-5931.2024.06.001