1.东南大学电气工程学院,江苏省南京市 210096
2.联通支付有限公司,北京市 100032
3.燕山大学电气工程学院,河北省秦皇岛市 066004
仇怡(2003—),女,硕士研究生,主要研究方向:负荷建模、电磁暂态仿真。E-mail:yiqiu@seu.edu.cn
徐一骏(1990—),男,通信作者,博士,教授,博士生导师,主要研究方向:电力系统不确定性分析、鲁棒调度。E-mail:yijunxu@seu.edu.cn
顾伟(1981—),男,博士,教授,博士生导师,主要研究方向:综合能源系统、电力系统仿真、分布式发电与微网、配电网等。E-mail:wgu@seu.edu.cn
收稿:2025-11-15,
修回:2026-02-27,
网络首发:2026-04-29,
纸质出版:2026-10-10
移动端阅览
仇怡,徐一骏,顾伟等.基于贝叶斯量测推断的数据中心热状态模型构建方法[J].电力系统自动化,2026,50(19):55-65.
QIU Yi,XU Yijun,GU Wei,et al.Thermal State Model Construction Method for Data Centers Based on Bayesian Inference from Measurements[J].Automation of Electric Power Systems,2026,50(19):55-65.
仇怡,徐一骏,顾伟等.基于贝叶斯量测推断的数据中心热状态模型构建方法[J].电力系统自动化,2026,50(19):55-65. DOI: 10.7500/AEPS20251115008.
QIU Yi,XU Yijun,GU Wei,et al.Thermal State Model Construction Method for Data Centers Based on Bayesian Inference from Measurements[J].Automation of Electric Power Systems,2026,50(19):55-65. DOI: 10.7500/AEPS20251115008.
随着数据中心规模与计算密度的持续增长,热管理已成为影响其能效与可靠性的关键因素之一,而构建准确的热模型是实施有效热管理的重要基础。针对数据中心的热状态建模问题,提出一种基于实时温度量测的贝叶斯数据中心热状态模型构建机制,通过结合热力学机理与量测驱动策略,实现对数据中心热状态的精准有效建模。首先,基于数据中心热力学传播结构,提出描述中央处理器、服务器机箱和环境温度的动态热模型,以刻画数据中心随时间变化的热状态;然后,针对数据中心热力学机理模型中存在的强非线性和先验不良问题,开发一种基于贝叶斯推断的分层自适应重要性采样技术。仿真结果表明,所提方法实现了对数据中心热状态的高精度建模,并在不同先验设定下验证了其高适用性。
As data centers continue to grow in scale and computational density
thermal management has become one of the critical factors affecting their energy efficiency and reliability. Building accurate thermal models is essential for implementing effective thermal management. Aiming at the modeling problem for thermal state of data centers
the construction mechanism of thermal state model for Bayesian data center based on real-time temperature measurement is proposed. First
based on the thermodynamic propagation structure of data centers
a dynamic thermal model is proposed to describe the central processing unit
server chassis
and environmental temperature
in order to characterize the thermal state of data centers over time. Then
to address the strong nonlinearity and prior defects in the thermodynamic mechanism model of data centers
a layered adaptive importance sampling technique based on Bayesian inference is developed. Simulation results demonstrate that the proposed method achieves high-accuracy modeling of thermal state models for data centers and exhibits high applicability under various prior settings.
丁肇豪 , 曹雨洁 , 张素芳 , 等 . 能源互联网背景下数据中心与电力系统协同优化(一):数据中心能耗模型 [J]. 中国电机工程学报 , 2022 , 42 ( 9 ): 3161 - 3176 .
Ding Zhaohao , Cao Yujie , Zhang Sufang , et al . Coordinated operation for data center and power system in the context of energy Internet (Ⅰ): energy demand management model of data center [J]. Proceedings of the CSEE , 2022 , 42 ( 9 ): 3161 - 3176 .
Jin C Q , Bai X L , Yang C , et al . A review of power consumption models of servers in data centers [J]. Applied Energy , 2020 , 265 : 114806 .
Wan J X , Duan Y D , Gui X , et al . SafeCool: safe and energy-efficient cooling management in data centers with model-based reinforcement learning [J]. IEEE Transactions on Emerging Topics in Computational Intelligence , 2023 , 7 ( 6 ): 1621 - 1635 .
可思为 , 董萍 , 马铭宇 , 等 . 考虑风光荷时空互补的多能源绿色数据中心多目标配置方法 [J]. 电力系统保护与控制 , 2024 , 52 ( 22 ): 22 - 33 .
Ke Siwei , Dong Ping , Ma Mingyu , et al . A multi-objective allocation method for multi-energy green data centers considering wind, solar and load spatial-temporal complementarity [J]. Power System Protection and Control , 2024 , 52 ( 22 ): 22 - 33 .
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 .
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/OL]. 电力系统自动化 , 2025-10-19 . http://doi.org/10.7500/AEPS20240414005 http://doi.org/10.7500/AEPS20240414005 .
Yu Lujie , Zhou Huan , Zhu Jiebei , et al . Thermal model and variable temperature operation strategy for data centers aimed at new energy integration [J/OL]. Automation of Electric Power Systems , 2025-10-19 . http://doi.org/10.7500/AEPS2024 0414005 http://doi.org/10.7500/AEPS20240414005 .
秦雪雪 , 李泽宁 , 薛屹洵 , 等 . 计及建筑热动态特性的数据中心时空协调两阶段鲁棒优化方法 [J]. 电力系统自动化 , 2025 , 49 ( 11 ): 59 - 69 .
Qin Xuexue , Li Zening , Xue Yixun , et al . Two-stage robust optimization method for spatio-temporal coordination of data center considering thermal dynamic characteristics of buildings [J]. Automation of Electric Power Systems . 2025 , 49 ( 11 ): 59 - 69 .
王天琪 , 于浩 , 赵金利 , 等 . 算力-热力灵活性协同的数据中心能量管理方法 [J]. 高电压技术 , 2024 , 50 ( 9 ): 4069 - 4079 .
Wang Tianqi , Yu Hao , Zhao Jinli , et al . Optimal energy management of data centers considering the synergy of computing power and thermal power flexibility [J]. High Voltage Engineering , 2024 , 50 ( 9 ): 4069 - 4079 .
郑芳芳 , 黄雨佳 , 王睿 , 等 . 计及数据中心算力等效的电热综合能源系统调度策略 [J/OL]. 中国电机工程学报 , 2025-10-19 . https://link.cnki.net/urlid/11.2107. TM.20250924.1020.002 https://link.cnki.net/urlid/11.2107.TM.20250924.1020.002 .
Zheng F , Huang Y , Wang R , et al . Scheduling strategy of electric-thermal integrated energy system considering computing power equivalence of data center [J/OL]. Proceedings of the CSEE , 2025-10-19 . https://link.cnki.net/urlid/11.2107. TM.20250924.1020.002 https://link.cnki.net/urlid/11.2107.TM.20250924.1020.002 .
Lin J P , Lin W W , Lin W J , et al . Thermal prediction for air-cooled data center using data driven-based model [J]. Applied Thermal Engineering , 2022 , 217 : 119207 .
Li Y L , Wen Y G , Tao D C , et al . Transforming cooling optimization for green data center via deep reinforcement learning [J]. IEEE Transactions on Cybernetics , 2020 , 50 ( 5 ): 2002 - 2013 .
Liu W W , Tong X X , Wang J Q , et al . Real-time temperature predictions via state-space model and parameters identification within rack-based cooling data centers [J]. Journal of Building Engineering , 2022 , 58 : 105013 .
朱介北 , 刘东昊 , 李炳森 , 等 . 基于CPU工作状态进行温度估算的数据中心服务器功耗模型 [J]. 电力系统自动化 , 2023 , 47 ( 14 ): 140 - 148 .
Zhu Jiebei , Liu Donghao , Li Bingsen , et al . Data center server power consumption model based on temperature estimation considering CPU working state [J]. Automation of Electric Power Systems , 2023 , 47 ( 14 ): 140 - 148 .
Wang Y W , Zhang Y R , Nörtershäuser D , et al . Model and data driven transient thermal system modelings for contained data centers [J]. Energy and Buildings , 2022 , 258 : 111790 .
Petra N , Petra C G , Zhang Z , et al . A Bayesian approach for parameter estimation with uncertainty for dynamic power systems [J]. IEEE Transactions on Power Systems , 2017 , 32 ( 4 ): 2735 - 2743 .
Pegoraro P A , Angioni A , Pau M , et al . Bayesian approach for distribution system state estimation with non-Gaussian uncertainty models [J]. IEEE Transactions on Instrumentation and Measurement , 2017 , 66 ( 11 ): 2957 - 2966 .
Xu Y J , Mili L , Korkali M , et al . An adaptive Bayesian parameter estimation of a synchronous generator under gross errors [J]. IEEE Transactions on Industrial Informatics , 2020 , 16 ( 8 ): 5088 - 5098 .
Biju V G , Schmitt A M , Engelmann B . Assessing the influence of sensor-induced noise on machine-learning-based changeover detection in CNC machines [J]. Sensors , 2024 , 24 ( 2 ): 330 .
崔杨 , 程禹烽 , 赵钰婷 , 等 . 考虑特性分类批处理负荷可调节能力的数据中心微网灵活性设备分布鲁棒容量配置方法 [J]. 电力自动化设备 , 2024 , 44 ( 7 ): 180 - 188 .
Cui Yang , Cheng Yufeng , Zhao Yuting , et al . Distributionally robust capacity allocation method for flexibility device of data center microgrid considering adjustable capability of characteristic classification batch processing loads [J]. Electric Power Automation Equipment , 2024 , 44 ( 7 ): 180 - 188 .
Fan X , Weber W D , Barroso L A . Power provisioning for a warehouse-sized computer [J]. ACM SIGARCH Computer Architecture News , 2007 , 35 ( 2 ): 13 - 23 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621