Siting Planning Method for Interconnected Data Centers Considering Decision-dependent Uncertainties

DENG Rongnan; SONG Meng; QIAO Lin; XIA Yurui; BAI Wenchao; GAN Wei

doi:10.7500/AEPS20250802002

您当前的位置：

首页 >

文章列表页 >

Siting Planning Method for Interconnected Data Centers Considering Decision-dependent Uncertainties

Basic Research | 更新时间：2026-11-04

- Siting Planning Method for Interconnected Data Centers Considering Decision-dependent Uncertainties
- Automation of Electric Power Systems Vol. 50, Issue 21, Pages: 164-173(2026)
- 作者机构：
  
  1.东南大学电气工程学院，江苏省南京市 210096
  2.国网辽宁省电力有限公司信息通信分公司，辽宁省沈阳市 110002
  3.卡迪夫大学工程学院，卡迪夫 CF24 3AA，英国
- 作者简介：
- 基金信息：
  
  National Key R&D Program of China(2024YFE0209900)
- DOI：10.7500/AEPS20250802002
  CLC：
- Received：02 August 2025，
  
  Revised：2025-12-08，
  
  Online First：05 February 2026，
  
  Published：10 November 2026
- 稿件说明：
移动端阅览
邓荣楠,宋梦,乔林等.计及决策依赖不确定性的互联数据中心选址规划方法[J].电力系统自动化,2026,50(21):164-173.

DENG Rongnan,SONG Meng,QIAO Lin,et al.Siting Planning Method for Interconnected Data Centers Considering Decision-dependent Uncertainties[J].Automation of Electric Power Systems,2026,50(21):164-173.
邓荣楠,宋梦,乔林等.计及决策依赖不确定性的互联数据中心选址规划方法[J].电力系统自动化,2026,50(21):164-173. DOI： 10.7500/AEPS20250802002.

DENG Rongnan,SONG Meng,QIAO Lin,et al.Siting Planning Method for Interconnected Data Centers Considering Decision-dependent Uncertainties[J].Automation of Electric Power Systems,2026,50(21):164-173. DOI： 10.7500/AEPS20250802002.

摘要

随着“东数西算”战略的深入实施，数据中心建设规模的快速增长使其选址规划需要更加精细化的考量。文中针对数据中心规划中选址与算力的决策依赖不确定性（DDU），提出了一种互联数据中心两阶段鲁棒优化方法。首先，构建互联数据中心决策依赖预算不确定集，以动态量化数据中心选址决策与算力需求波动的内生关联；然后，基于决策依赖不确定集，建立计及DDU的互联数据中心两阶段鲁棒混合整数规划模型，涵盖土地、设备、电力、碳排放等多维度成本要素；最后，针对传统列与约束生成（CCG）算法无法处理DDU的问题，定制化设计了改进的Benders&CCG算法，以快速精确求解互联数据中心规划的DDU问题。算例结果表明，与传统决策无关不确定性方法相比，所提方法的总成本降低了4.73%，并且在极端场景下仍能保障算力需求。灵敏度分析进一步验证了所提模型对需求波动的强适应性。研究为高资本密集、长周期的互联数据中心规划提供了兼顾经济性与鲁棒性的决策工具，能够进一步助力双碳目标与数字经济协同发展。

Abstract

With the deepening implementation of the “East Data

West Computing” strategy

the rapid growth of data center construction scale requires more refined siting planning. This paper addresses the decision-dependent uncertainty (DDU) in siting and computing power of data center planning

and proposes a two-stage robust optimization method for interconnected data centers. First

a decision-dependent budget uncertainty set is constructed to dynamically quantify the endogenous coupling between data center siting decisions and fluctuations in computing power demand. Then

based on the decision-dependent uncertainty set

a two-stage robust mixed-integer programming model that accounts for DDU is established for interconnected data centers

incorporating multi-dimensional cost components including land

equipment

electricity

and carbon emission. Finally

to overcome the inability of the conventional column-and-constraint generation (CCG) algorithm to handle DDU

an improved Benders&CCG algorithm is custom-designed to rapidly and accurately solve the DDU problem in interconnected data center planning. Case results show that

compared with the conventional decision-independent uncertainty method

the proposed method reduces the total cost by 4.73% while still guaranteeing computing power demand in extreme scenarios. Sensitivity analysis further verifies the strong adaptability of the proposed model to demand fluctuations. This study provides a decision-making tool that balances economic efficiency and robustness for the planning of interconnected data centers

which are characterized by high capital intensity and long planning horizons

and can further support the coordinated development of the goals of carbon emission peaking and carbon neutrality and the digital economy.

关键词

Keywords

references

关于深入实施“东数西算”工程加快构建全国一体化算力网的实施意见［EB/OL］.［ 2025-06-07 ］. https：//www.gov.cn/zhengce/zhengceku/202401/content_6924596.htm https://www.gov.cn/zhengce/zhengceku/202401/content_6924596.htm .

Opinions on deeply implementing the “East Data ， West Computing” project and accelerating the construction of a national integrated computing power network ［EB/OL］. ［ 2025-06-07 ］. https：//www.gov.cn/zhengce/zhengceku/202401/content_6924 596.htm https://www.gov.cn/zhengce/zhengceku/202401/content_6924596.htm .

Chu W X ， Wang C C . A review on airflow management in data centers ［J］. Applied Energy ， 2019 ， 240 ： 84 - 119 .

2025年中国数据中心行业：算力革命下的“新基建”黄金赛道［EB/OL］.［ 2025-07-25 ］. https：//www.chinairn.com/news/20250618/112204320.shtml https://www.chinairn.com/news/20250618/112204320.shtml .

China’s data center industry in 2025 ： the golden track of “new infrastructure” under the computing power revolution ［EB/OL］. ［ 2025-07-25 ］. https：//www.chinairn.com/news/20250618/112204320.shtml https://www.chinairn.com/news/20250618/112204320.shtml .

Song M ， Yan X Y ， Wang X D ， et al . Optimal scheduling strategy of networked data centers in multiple transactive energy markets ［J/OL］. CSEE Journal of Power and Energy Systems ［ 2024-07-24 ］. https：//xplorestaging.ieee.org/document/1060 9300 https://xplorestaging.ieee.org/document/10609300 .

Chen M ， Gao C W ， Song M ， et al . Internet data centers participating in demand response： a comprehensive review ［J］. Renewable and Sustainable Energy Reviews ， 2020 ， 117 ： 109466 .

Lam P T I ， Lai D ， Leung C K ， et al . Data centers as the backbone of smart cities： principal considerations for the study of facility costs and benefits ［J］. Facilities ， 2021 ， 39 （ 1/2 ）： 80 - 95 .

Hamilton S . Challenges in urban data center design ［C］// INTER-NOISE and NOISE-CON Congress and Conference ， 2024 ： 716 - 723 .

Dayarathna M ， Wen Y G ， Fan R . Data center energy consumption modeling： a survey ［J］. IEEE Communications Surveys & Tutorials ， 2016 ， 18 （ 1 ）： 732 - 794 .

Ismail L ， Materwala H . Computing server power modeling in a data center： survey， taxonomy， and performance evaluation ［J］. ACM Computing Surveys ， 2021 ， 53 （ 3 ）： 1 - 34 .

Vafamehr A ， Khodayar M E ， Manshadi S D ， et al . A framework for expansion planning of data centers in electricity and data networks under uncertainty ［J］. IEEE Transactions on Smart Grid ， 2019 ， 10 （ 1 ）： 305 - 316 .

俞露杰，周欢，朱介北，等 . 面向新能源消纳的数据中心热力学模型和变温运行策略［J］. 电力系统自动化， 2026 ， 50 （ 19 ）： 44 - 54 .

Yu Lujie ， Zhou Huan ， Zhu Jiebei ， et al . Thermodynamic model and variable-temperature operation strategy of data centers for renewable energy accomodation ［J］. Automation of Electric Power Systems ， 2026 ， 50 （ 19 ）： 44 - 54 .

Li C L ， Yu X B ， Zhao W X . An integrated approach to site selection for a big data center using PROMETHEE-MCGP methodology ［J］. Journal of Intelligent & Fuzzy Systems ， 2021 ， 41 （ 6 ）： 6495 - 6515 .

Pahlevan A ， Qu X Y ， Zapater M ， et al . Integrating heuristic and machine-learning methods for efficient virtual machine allocation in data centers ［J］. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems ， 2018 ， 37 （ 8 ）： 1667 - 1680 .

Turek D ， Radgen P . Optimized data center site selection—mesoclimatic effects on data center energy consumption and costs ［J］. Energy Efficiency ， 2021 ， 14 （ 3 ）： 33 .

Dong H Q ， Wang L Y ， Zhang X C ， et al . A two-stage stochastic collaborative planning approach for data centers and distribution network incorporating demand response and multivariate uncertainties ［J］. Journal of Cleaner Production ， 2024 ， 451 ： 141482 .

Ekhtiari M ， Zandieh M ， Tirkolaee E B . Optimizing the dam site selection problem considering sustainability indicators and uncertainty： an integrated decision-making approach ［J］. Journal of Cleaner Production ， 2023 ， 428 ： 139240 .

Chen M ， Gao C W ， Li Z Y ， et al . Aggregated model of data network for the provision of demand response in generation and transmission expansion planning ［J］. IEEE Transactions on Smart Grid ， 2021 ， 12 （ 1 ）： 512 - 523 .

Peng C ， Li J L ， Wang S S . Two-stage robust facility location problem with multiplicative uncertainties and disruptions ［C］// International Conference on Service Systems and Service Management ， 2017 .

Du B ， Zhou H ， Leus R . A two-stage robust model for a reliable p-center facility location problem ［J］. Applied Mathematical Modelling ， 2020 ， 77 ： 99 - 114 .

李鸿，朱继忠，董瀚江 . 考虑协变量因素的多能微电网两阶段分布鲁棒优化调度［J］. 中国电机工程学报， 2025 ， 45 （ 3 ）： 822 - 833 .

Li Hong ， Zhu Jizhong ， Dong Hanjiang . Two-stage distributionally robust optimization scheduling for multi-energy microgrid considering covariate factors ［J］. Proceedings of the CSEE ， 2025 ， 45 （ 3 ）： 822 - 833 .

Haghighat H ， Wang W ， Zeng B . Robust microgrid capacity investment with endogenous and exogenous uncertainties ［J］. IEEE Transactions on Smart Grid ， 2024 ， 15 （ 3 ）： 2480 - 2492 .

王灿，张雪菲，凌凯，等 . 基于区间概率不确定集的微电网两阶段自适应鲁棒优化调度［J］. 中国电机工程学报， 2024 ， 44 （ 5 ）： 1750 - 1763 .

Wang Can ， Zhang Xuefei ， Ling Kai ， et al . Two-stage adaptive robust optimal scheduling based on the interval probability uncertainty set for microgrids ［J］. Proceedings of the CSEE ， 2024 ， 44 （ 5 ）： 1750 - 1763 .

Zhuang K Q ， Wang Z ， Yang N ， et al . Robust optimization-driven strategy for dynamic planning of power transmission networks ［C］// 3rd International Conference on Energy and Electrical Power Systems （ICEEPS）， 2024 .

杜敏，刘绚，周元刚 . 考虑极端事件下的高比例可再生能源电力系统韧性增强策略［J］. 电力系统自动化， 2023 ， 47 （ 12 ）： 19 - 27 .

Du Min ， Liu Xun ， Zhou Yuangang . Resilience enhancement strategy for power system with high proportion of renewable energy considering extreme events ［J］. Automation of Electric Power Systems ， 2023 ， 47 （ 12 ）： 19 - 27 .

黄馨仪，刘明波，林舜江，等 . 考虑风电不确定性的输配电系统鲁棒经济调度分布式算法［J］. 电力系统自动化， 2025 ， 49 （ 4 ）： 165 - 177 .

Huang Xinyi ， Liu Mingbo ， Lin Shunjiang ， et al . Distributed algorithm for robust economic dispatch of integrated transmission and distribution system considering wind power uncertainty ［J］. Automation of Electric Power Systems ， 2025 ， 49 （ 4 ）： 165 - 177 .

Zeng B ， Wang W . Two-stage robust optimization with decision dependent uncertainty ［PP/OL］. ［ 2025-05-03 ］. https：//arxiv.org/abs/2203.16484 https://arxiv.org/abs/2203.16484 .

Zhang Y F ， Liu F ， Su Y F ， et al . Two-stage robust optimization under decision dependent uncertainty ［J］. IEEE/CAA Journal of Automatica Sinica ， 2022 ， 9 （ 7 ）： 1295 - 1306 .

Goerigk M ， Lendl S ， Wulf L . Two-Stage robust optimization problems with two-stage uncertainty ［J］. European Journal of Operational Research ， 2022 ， 302 （ 1 ）： 62 - 78 .

Faiz T I ， Noor-E-Alam M . Data center supply chain configuration design： a two-stage decision approach ［J］. Socio-Economic Planning Sciences ， 2019 ， 66 ： 119 - 135 .

Bai W C ， Song M ， Gao C W ， et al . Resilient microgrid formation strategy considering the uncertainties of ice-storm outage mitigation ［J］. IEEE Transactions on Smart Grid ， 2026 ， 17 （ 1 ）： 30 - 44 .

Yang Z H ， Trivedi A ， Liu H M ， et al . Two-stage robust optimization strategy for spatially-temporally correlated data centers with data-driven uncertainty sets ［J］. Electric Power Systems Research ， 2023 ， 221 ： 109443 .

李明睿，朱介北，俞露杰，等 . 实现新能源最大利用的多数据中心自适应负荷调度算法［J］. 中国电机工程学报， 2025 ， 45 （ 6 ）： 2071 - 2083 .

Li Mingrui ， Zhu Jiebei ， Yu Lujie ， et al . Adaptive spatio-temporal tasks scheduling algorithm in regional interconnected data centers ［J］. Proceedings of the CSEE ， 2025 ， 45 （ 6 ）： 2071 - 2083 .

Lee H S ， Chang B Y . Economic analysis of micro data center construction and utilization business ［J］. Journal of Next-Generation Convergence Information Services Technology ， 2021 ， 10 （ 6 ）： 619 - 632 .

曾博，孟自帅，董嘉路，等 . 考虑电-水耦合灵活性的数据中心与城市配电-水网协同规划研究［J］. 电工技术学报， 2025 ， 40 （ 23 ）： 7554 - 7569 .

Zeng Bo ， Meng Zishuai ， Dong Jialu ， et al . Research on synergistic planning of data center and urban electricity-water distribution networks considering electricity-water interdependent flexibility ［J］. Transactions of China Electrotechnical Society ， 2025 ， 40 （ 23 ）： 7554 - 7569 .

兰洲，蒋晨威，谷纪亭，等 . 促进可再生能源发电消纳和碳减排的数据中心优化调度与需求响应策略［J］. 电力建设， 2022 ， 43 （ 4 ）： 1 - 9 .

Lan Zhou ， Jiang Chenwei ， Gu Jiting ， et al . Optimal dispatch and demand response strategies of data centers for promoting accommodation of renewable energy generation and reducing carbon emission ［J］. Electric Power Construction ， 2022 ， 43 （ 4 ）： 1 - 9 .

Chen S R ， Li P ， Ji H R ， et al . Operational flexibility of active distribution networks with the potential from data centers ［J］. Applied Energy ， 2021 ， 293 ： 116935 .

文淅宇，朱继忠，李盛林，等 . 基于时空协同的多数据中心虚拟电厂低碳经济调度策略［J］. 电力系统自动化， 2024 ， 48 （ 18 ）： 56 - 65 .

Wen Xiyu ， Zhu Jizhong ， Li Shenglin ， et al . Low-carbon economic dispatch for multiple data center virtual power plant based on spatio-temporal collaboration ［J］. Automation of Electric Power Systems ， 2024 ， 48 （ 18 ）： 56 - 65 .

Yan R J ， Wang J J ， Wang J H ， et al . A two-stage stochastic-robust optimization for a hybrid renewable energy CCHP system considering multiple scenario-interval uncertainties ［J］. Energy ， 2022 ， 247 ： 123498 .

关于2024年可再生能源电力消纳责任权重及有关事项的通知［EB/OL］.［ 2025-09-09 ］. https：//www.ncsti.gov.cn/kjdt/tzgg/202408/t20240805_174155.html https://www.ncsti.gov.cn/kjdt/tzgg/202408/t20240805_174155.html .

Notice on the responsibility weight for the consumption of renewable energy power in 2024 and related matters ［EB/OL］. ［ 2025-09-09 ］. https：//www.ncsti.gov.cn/kjdt/tzgg/202408/t20240805_174155.html https://www.ncsti.gov.cn/kjdt/tzgg/202408/t20240805_174155.html .

近三年张家口可再生能源装机规模增长 1 500 万千瓦，涨幅与示范区获批六年持平［EB/OL］.［ 2025-09-09 ］. http：//www.zjknews.com/news/nengyuan/202412/12/453962.html http://www.zjknews.com/news/nengyuan/202412/12/453962.html .

In the past three years， the installed capacity of renewable energy in Zhangjiakou has increased by 15 million kilowatts ， with the growth rate being on par with that of the six years since the approval of the demonstration zone ［EB/OL］. ［ 2025-09-09 ］. http：//www.zjknews.com/news/nengyuan/202412/12/453962.html http://www.zjknews.com/news/nengyuan/202412/12/453962.html .

数据中心白皮书［R］. 北京：中国信息通信研究院， 2023 .

White paper on data center ［R］. Beijing ： China Academy of Information and Communications Technology ， 2023 .

Zhang M Z ， Li W D ， Yu S S ， et al . Optimal day-ahead large-scale battery dispatch model for multi-regulation participation considering full timescale uncertainties ［J］. Renewable and Sustainable Energy Reviews ， 2024 ， 189 ： 113963 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Green Power Directly-connected Data Centers: Coupling Logic, Key Technologies, and Application Modes

Optimal Allocation Method for Centralized Backup Energy Storage of Data Center Clusters Under Shared Framework

Machine Learning Based Distributionally Robust Optimization and Coordinated Operation of Electric Power, Computing Power, and Thermal Power in Data Centers

Method and Practice of Computing Power-Electric Power Coordination Based on Idle Computing Power Scheduling

Coordinated Optimization Method for Computing Power and Electric Power in Data Centers Considering Sequential Flexibility of Tasks

Related Author

DING Hao

TONG Jie

YI Chenle

WANG Zhanbo

CHEN Hongyin

YU Yaoxian

LI Bingle

YE Chengjin

Related Institution

School of Electrical and Electronic Engineering, North China Electric Power University

China Electric Power Research Institute

College of Electrical Engineering, Zhejiang University

Guizhou Power Grid Co., Ltd.

School of Electrical Engineering and Automation, Wuhan University

⁰