As data centres continue to expand and energy consumption rises, improving energy efficiency and achieving low-carbon operation remain major challenges. In this context, accurate prediction of temperature and thermal load is regarded as a core element of intelligent management. In this context, research progress on temperature and thermal load prediction in data centres was systematically reviewed. The research background and significance were summarised, and the coupling mechanisms among energy consumption, cooling, and thermal environment that influence efficiency optimisation were analysed. Core concepts related to temperature and thermal load prediction were introduced, and existing work was classified into physics-driven modelling, which is characterized by mechanistic consistency and physical interpretability; data-driven approaches, which rely on monitoring data for efficient prediction; and hybrid modelling, which integrates both perspectives to balance accuracy, generalisation, and interpretability. The differences and complementarities between steady-state and transient prediction methods were compared, and their application value in energy-efficiency assessment, cooling optimisation, dynamic regulation, and risk warning was discussed. Future trends were highlighted, indicating that multi-scale coordination, cross-scenario adaptation, and integrated prediction-control were expected to become important research directions. These findings are expected to provide theoretical support and methodological guidance for the development of intelligent and low-carbon data centres.
LI Jin, REN Zi-yuan, LI Lei-xiao, LIU Dong-jiang, WAN Jian-xiong, LIN Hao.
State of Art and Prospects of Data Center Temperature and Thermal Load Prediction[J].
Science Technology and Engineering, 2026, 26(10): 4027-4047 DOI:10.12404/j.issn.1671-1815.2506829
参考文献[15]将数据中心的运行视为一个由物理层、建模层和调度层相互作用的整体,如图1所示。底层的基础设施包括机柜、服务器以及典型的冷热通道布局。冷空气通过架高地板由机房空调(computer room air conditioner, CRAC)送入冷通道,在穿过服务器时带走芯片产生的热量,形成的热气流回流至热通道,最终返回CRAC完成循环。这种典型的冷热通道分离设计不仅是现代数据中心的基础架构,也是决定温度分布与冷却负载的关键因素。由于虚拟机负载往往呈现动态变化,局部服务器在高负载下极易形成热点,从而对冷却能耗与调度策略产生显著影响。
在此基础上,最上层的系统管理层承担了策略执行的功能,不同于传统研究中单纯依赖资源利用率进行调度的方法,本文提出的调度机制由整体热模型驱动。虚拟机的放置与迁移不仅考虑中央处理器(central processing unit, CPU)利用率和资源剩余情况,还结合服务器进风温度和芯片热阈值,以降低局部热点形成的风险。同时,CRAC的送风设定点能够根据实时温度分布动态调整,从而在计算与冷却能耗之间实现协同优化。由此形成的闭环机制,使数据中心的运行不再是“计算”和“制冷”的分割管理,而演化为一个在物理约束、能耗建模与调度策略之间不断迭代和反馈的动态过程。
为进一步反映运行过程中的动态行为,Zhou等[26]基于质量与能量平衡原理提出动态模型,以描述风冷数据中心内复杂的质量和能量流动。该模型确定了CRAC运行状态,包括送风温度(supply air temperature,SAT)和变频驱动器(variable frequency drive,VFD)以及再循环热空气对节点入口温度的影响,并给出了节点i入口温度的离散化定量表示公式为
紧凑型模型会把整个机柜、CRAC、冷热通道等部件抽象为耦合节点系统,以此简化对热过程的建模。VanGilder等[34]提出了一种数据中心中典型的机房空气处理器(computer room air conditioner, CRAH)冷却系统的紧凑型模型,将冷却装置理想化为热交换器,并串联额外热质量以近似整体过程。但其基于理想化假设的结构抽象难以准确反映复杂瞬态传热过程,跨工况适用性有限。在此基础上,Pardey等[35]提出服务器级集总电容模型,通过实验标定热容与热效率增强了模型的可验证性,但其将服务器视为均质热容体,难以反映内部热耦合特性,在动态条件下仍可能产生偏差。此外,Athavale等[36]通过数据中心对紧凑模型的需求验证4种数据驱动模型作为紧凑方案的可行性,拓展了紧凑模型在温度预测中的应用边界。但由于模型主要依赖CFD数据训练,其外推性能受限,对复杂机房拓扑的泛化能力仍不足。
POD方法是一种典型的降阶建模(reduced order modeling, ROM)技术,它通过从高维数值解或实验数据中提取主要模态,实现对复杂物理场的低维近似,从而在保证主要物理一致性的同时显著降低计算复杂度。因此,基于POD构建的降阶模型常被称为POD-ROM。在数据中心研究中,POD-ROM已被广泛用于温度预测与热管理[44]。POD已被应用于单参数模型、双参数模型、稳态和瞬态场景,以及基于实验数据或计算数据开发的模型。
在典型的POD-ROM流程中,建模可分为离线与在线两个阶段:在离线阶段,通过CFD或实验获取大量快照数据,构建快照矩阵并采用奇异值分解(singular value decomposition, SVD)提取主模态,从而形成能够表征系统主要热特征的低维基底;在在线阶段,针对给定工况,通过Galerkin投影、插值或回归等方式估计POD系数,并据此快速重建温度场,实现对三维热环境的预测,如图4所示。早期的研究,如Samadiani等[44]系统性地将POD应用于数据中心热建模的研究之一,证明其可在保证预测精度的同时计算效率提升数十倍,对于机架级热设计具有重要意义。但该方法主要针对单一工况,难以应对多参数条件下的运行变化。为此,Phan等[46]将POD扩展到多参数场景,验证了其在不同入口温度、流量和负载条件下的预测能力,为POD在复杂运行环境中的应用提供了支撑。
在数据驱动方法的基础上,研究逐渐转向结构融合模型,通过耦合时序、空间与优化机制实现更强的预测与泛化能力。早期研究多以单一结构为核心,如Wang等[54]在数据中心温度预测中提出的基于多层感知机(multi-layer perceptron,MLP)的LSTM超参数优化方法,在一定程度上改善了温度预测性能,但在长时依赖建模与多尺度特征提取方面仍存在局限性。为增强时空联合建模能力,Wang等[13]提出了如图7所示的CNN-BiLSTM-Attention(convolutional neural network-Bi-directional long short term memory-attention)融合框架作为热预测模型,其中CNN提取空间特征,BiLSTM捕捉双向时序依赖,注意力机制则强化关键特征权重,使模型在复杂环境下展现出更稳定的预测表现。宋越等[69]基于新疆电子研究所股份有限公司的数据中心IT设备区域的PDU实测数据,构建了CNN-BiLSTM-Attention能耗预测模型,并在多种基线方法之上取得更优结果,表明这一融合范式在真实工程场景中具有良好适用性。
WangYongzhen, SongKuo, HanKai, et al. Full-stack linkage of high-density cabinets in data centers considering computing-electric-thermal power synergy[J]. Science China: Technological Sciences, 2025, 55(2): 213-232.
WangYongzhen, TangHao, WeiYiming, et al. Comprehensive energy consumption and flexibility forecast of data centers in China[J]. Journal of Beijing Institute of Technology (Social Sciences Edition), 2025, 27(2): 12-18.
[5]
KanburB B, WuC, FanS, et al. System-level experimental investigations of the direct immersion cooling data center units with thermodynamic and thermoeconomic assessments[J]. Energy, 2021, 217: 119373-119387.
[6]
田辉, 田峻超, 穆钊, 等. 中小型数据中心 PUE 值与可用性平衡方法的研究[J]. 网络安全技术与应用, 2021(2): 66-67.
[7]
TianHui, TianJunchao, MuZhao, et al. Study on the balance method between PUE and availability of small-and medium-sized data centers[J]. Network Security Technology & Application, 2021(2): 66-67.
[8]
MengX, ZhouJ, ZhangX, et al. Optimization of the thermal environment of a small-scale data center in China[J]. Energy, 2020, 196: 117080-117094.
[9]
LuH, ZhangZ, YangL. A review on airflow distribution and management in data center[J]. Energy and Buildings, 2018, 179: 264-277.
[10]
ZhaoR, DuY, YangX, et al. A critical review on the thermal management of data center for local hotspot elimination[J]. Energy and Buildings, 2023, 297: 113486-113502.
[11]
LinJ, LinW, LinW, et al. Thermal prediction for air-cooled data center using data driven-based model[J]. Applied Thermal Engineering, 2022, 217: 119207-119217.
[12]
LiuW, TongX, WangJ, 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: 105013-105027.
[13]
TongX, WangJ, LiuW, et al. A time-varying state-space model for real-time temperature predictions in rack-based cooling data centers[J]. Applied Thermal Engineering, 2023, 230: 120737-120749.
[14]
ChenX, TuR, LiM, et al. Hot spot temperature prediction and operating parameter estimation of racks in data center using machine learning algorithms based on simulation data[J]. Building Simulation, 2023, 16(11): 2159-2176.
[15]
ShoukourianH, KranzlmüllerD. Forecasting power-efficiency related key performance indicators for modern data centers using LSTMs[J]. Future Generation Computer Systems, 2020, 112: 362-382.
[16]
WangN, GuoY, HuangC, et al. Multi-scale collaborative modeling and deep learning-based thermal prediction for air-cooled data centers: an innovative insight for thermal management[J]. Applied Energy, 2025, 377: 124568-124585.
GuoXiaodong, LuoHongwu, YaoJianqiang, et al. Application prospect of intelligent monitoring and predictive maintenance technology in enterprise data centers[J]. Information Systems Engineering, 2021(12): 113-116.
[19]
LinJ, LinW, WuW, et al. Energy-aware virtual machine placement based on a holistic thermal model for cloud data centers[J]. Future Generation Computer Systems, 2024, 161: 302-314.
WangChao. Design and implementation of a software automatic operation and maintenance platform for data centers[J]. Science and Technology & Innovation, 2025(11): 96-99.
GaoYujie, XuQingshan. Numerical simulation of thermal environment and optimal design of airflow uniformity in data center[J]. Power Demand Side Management, 2024, 26(6): 75-80.
[24]
ChuW X, WangC C. A review on airflow management in data centers[J]. Applied Energy, 2019, 240: 84-119.
[25]
NadaS A, SaidM A, RadyM A. CFD investigations of data centers’ thermal performance for different configurations of CRACs units and aisles separation[J]. Alexandria Engineering Journal, 2016, 55(2): 959-971.
GuChangcheng, HanChengfu, GuoNan, et al. CFD simulation analysis of air distribution design of a data center in Northern China[J]. Telecom Power Technology, 2023, 40(1): 4-12.
YinJiahui, ZhuBing, ZhangYiming, et al. Machine learning-based prediction of steady-state thermal parameters in data centers[J]. Computer Era, 2023(11): 71-75.
[30]
TangY Q, FangW Z, ZhengC Y, et al. Applications of POD-based reduced order model to the rapid prediction of velocity and temperature in data centers[J]. Applied Thermal Engineering, 2025, 263: 125310-125321.
[31]
DaiY, ZhaoJ, ZhangX, et al. Thermal full-field prediction of an air-cooled data center using a novel multi-scale approach based on POD and CFD coupling[J]. Energy and Buildings, 2024, 307: 113992-114009.
[32]
WangY, BaiX, FuY, et al. Field experiment and numerical simulation for airflow evaluation in a data center with row-based cooling[J]. Energy and Buildings, 2023, 294: 113231-113245.
[33]
TangQ, MukherjeeT, GuptaS K S, et al. Sensor-based fast thermal evaluation model for energy efficient high-performance datacenters[C]// Fourth International Conference on Intelligent Sensing and Information Processing. Bangalore: IEEE, 2006: 203-208.
[34]
ZhouR, WangZ, BashC E, et al. Modeling and control for cooling management of data centers with hot aisle containment[J]. Engineering Environmental Science, 2011. DOI: 10.1115/IMECE2011-62506.
[35]
XuS, ZhangH, WangZ. Thermal management and energy consumption in air, liquid, and free cooling systems for data centers: a review[J]. Energies, 2023, 16(3): 1279-1304.
[36]
WangY, ZhangY, NörtershäuserD, et al. Model and data driven transient thermal system modelings for contained data centers[J]. Energy and Buildings, 2022, 258: 111790-111804.
[37]
IbrahimM, GondipalliS, BhopteS, et al. Numerical modeling approach to dynamic data center cooling[C]// 12th IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems. Las Vegas: IEEE, 2010: 1-7.
[38]
ZhangX S, VanGilderJ W. Real-time data center transient analysis[C]// ASME 2011 Pacific Rim Technical Conference and Exhibition on Packaging and Integration of Electronic and Photonic Systems, MEMS and NEMS. Portland: ASMEDC, 2011: 471-477.
[39]
ErdenH S, KhalifaH E, SchmidtR R. A hybrid lumped capacitance-CFD model for the simulation of data center transients[J]. HVAC&R Research, 2014, 20(6): 688-702.
[40]
DuY, ZhouZ, YangX, et al. Dynamic thermal environment management technologies for data center: a review[J]. Rene-wable and Sustainable Energy Reviews, 2023, 187: 113761-113781.
[41]
AsgariS, MoazamigoodarziH, TsaiP J, et al. Hybrid surrogate model for online temperature and pressure predictions in data centers[J]. Future Generation Computer Systems, 2021, 114: 531-547.
[42]
VanGilderJ W, HealeyC M, CondorM, et al. A compact cooling-system model for transient data center simulations[C]// 17th IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm). San Diego: IEEE, 2018: 707-715.
[43]
PardeyZ M, DemetriouD W, ErdenH S, et al. Proposal for standard compact server model for transient data center simulations[J]. ASHRAE Transactions, 2015, 121: 413-421.
[44]
AthavaleJ, YodaM, JoshiY. Comparison of data driven modeling approaches for temperature prediction in data centers[J]. International Journal of Heat and Mass Transfer, 2019, 135: 1039-1052.
[45]
PiersonJ M, StolfP, SunH, et al. MILP formulations for spatio-temporal thermal-aware scheduling in cloud and HPC datacenters[J]. Cluster Computing, 2020, 23(2): 421-439.
[46]
SunH, StolfP, PiersonJ M. Spatio-temporal thermal-aware scheduling for homogeneous high-performance computing datacenters[J]. Future Generation Computer Systems, 2017, 71: 157-170.
[47]
LinJ, LinW, HuangH, et al. Thermal modeling and therma-laware energy saving methods for cloud data centers: a review[J]. IEEE Transactions on Sustainable Computing, 2024, 9(3): 571-590.
[48]
MoazamigoodarziH, GuptaR, PalS, et al. Modeling temperature distribution and power consumption in IT server enclosures with row-based cooling architectures[J]. Applied Energy, 2020, 261. DOI: 10.1016/j.apenergy.2019.114355.
[49]
SongZ, MurrayB T, SammakiaB. A dynamic compact thermal model for data center analysis and control using the zonal method and artificial neural networks[J]. Applied Thermal Engineering, 2014, 62(1): 48-57.
[50]
MoazamigoodarziH, PalS, GhoshS, et al. Real-time temperature predictions in IT server enclosures[J]. International Journal of Heat and Mass Transfer, 2018, 127: 890-900.
[51]
MirhoseininejadS, MoazamigoodarziH, BadawyG, et al. Joint data center cooling and workload management: a thermal-aware approach[J]. Future Generation Computer Systems, 2020, 104: 174-186.
[52]
SamadianiE, JoshiY. Proper orthogonal decomposition for reduced order thermal modeling of air cooled data centers[J]. Journal of Heat Transfer, 2010, 132(7). DOI: 10.1115/1.4000978.
[53]
FouladiK, WemhoffA P, Silva-LlancaL, et al. Optimization of data center cooling efficiency using reduced order flow modeling within a flow network modeling approach[J]. Applied Thermal Engineering, 2017, 124: 929-939.
[54]
PhanL, LinC X. Reduced order modeling of a data center model with multi-parameters[J]. Energy and Buildings, 2017, 136: 86-99.
ShiTaotao, ZhaoAiguo, ZhuXu, et al. Improved orthogonal decomposition model for temperature field prediction of data center based on deep belief network model[J]. Chinese Journal of Refrigeration Technology, 2023, 43(2): 35-42.
[57]
KansaraN, KattiR, NematiK. Neural network modeling in model-based control of a data center[J]. Computer Science Engineering, 2015.DOI: 10.1115/IPACK2015-48684.
[58]
De LorenziF, VömelC. Neural network-based prediction and control of air flow in a data center[J]. Journal of Thermal Science and Engineering Applications, 2012, 4(2). DOI: 10.1115/1.4005605.
[59]
AkbarS, LiR, WaqasM, et al. Server temperature prediction using deep neural networks to assist thermal-aware scheduling[J]. Sustainable Computing: Informatics and Systems, 2022, 36. DOI: 10.1016/j.suscom.2022.100809.
[60]
NisaE C, KuanY D, LinC H. Leveraging multi-zone building data with machine learning-based models and genetic algorithms to optimize air handling units[J]. Journal of Building Engineering, 2024, 96: 110411-110429.
[61]
GillS S, TuliS, ToosiA N, et al. ThermoSim: Deep learning based framework for modeling and simulation of thermal-aware resource management for cloud computing environments[J]. Journal of Systems and Software, 2020, 166: 110596-110616.
[62]
AbbasimehrH, ShabaniM, YousefiM. An optimized model using LSTM network for demand forecasting[J]. Computers & Industrial Engineering, 2020, 143: 106435-106448.
[63]
WangS, MaC, XuY, et al. A hyperparameter optimization algorithm for the LSTM temperature prediction model in data center[J]. Scientific Programming, 2022, 2022: 1-13.
XuYixuan, WuWeiguo, WangSimin, et al. Data center tempera-ture prediction algorithm based on long short-term memory network[J]. Computer Technology and Development, 2019, 29(12): 1-7.
[66]
YiD, ZhouX, WenY, et al. Efficient compute-intensive job allocation in data centers via deep reinforcement learning[J]. IEEE Transactions on Parallel and Distributed Systems, 2020, 31(6): 1474-1485.
LiuMin, GongHao, DaiWenhai, et al. Data center server energy consumption prediction based on xLSTM[J/OL]. Journal of Harbin University of Science and Technology[2026-03-19]. https://kns.cnki.net/kcms/detail/23.1404.N.20250507.0937.006.html.
WangXu, TuoYa, LiXin, et al. Temperature prediction model for power data centers based on GRU[J]. Journal of Harbin University of Science and Technology, 2024, 29(6): 101-111.
[71]
PengY H, LeeC M, TungK Y, et al. Rack inlet temperature prediction based on deep learning[C]// 25th International Confe-rence on Mechatronics Technology (ICMT). Kaohsiung: IEEE, 2022: 1-4.
[72]
VaswaniA, ShazeerN, ParmarN, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 2017: 30-41.
ZhuXu, HeXiao, GaoJian, et al. Fast reconstruction andprediction method of three-dimensional temperature field in data center room based on Transformer[J]. Posts and Telecommunications Design Technology, 2024(10): 1-6.
[75]
ZhangW, ZhouH, BaoX, et al. Outlet water temperature prediction of energy pile based on spatial-temporal feature extraction through CNN-LSTM hybrid model[J]. Energy, 2023, 264: 126190-126204.
YanLi, ZhangKai, XuHao, et al. Abnormal detection based on graph attention mechanisms and Transformer[J]. Acta Electronica Sinica, 2022, 50(4): 900-908.
[78]
LiJ, LiuD, MaG, et al. DBFF-GRU: dual-branch temporal feature fusion network with fast GRU for multivariate time series forecasting[J]. Applied Intelligence, 2025, 55(7). DOI: 10.1007/s10489-025-06447-9.
[79]
ShaQ, YangJ, ShaoR, et al. Prediction of air-conditioning outlet temperature in data centers based on graph neural networks[J]. Energies, 2025, 18(7). DOI: 10.3390/en18071803.
LiHui. Research on predictive control optimization method for data center cooling model based on graph convolutional neural network[J]. Chinese Journal of Refrigeration Technology, 2024, 44(4): 72-77.
[82]
HanK, WangY, ChenH, et al. A survey on vision transformer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 87-110.
YangMengya, ZhaoYan, XueLiang, et al. Deep hashing method based on improved Vision Transformer[J]. Journal of Shaanxi university of Science & Technology, 2025, 43(4): 183-189.
SongYue, JinSheng, LinLi, et al. Research on energy consumption prediction model of industrial data center IT equipment based on CNN-BiLSTM-Attention[J]. Application of Electronic Technique, 2025, 51(10): 63-68.
[87]
LinJ, LinW, LinW, et al. Multi-objective cooling control optimization for air-liquid cooled data centers using TCN-BiGRU-Attention-based thermal prediction models[J]. Building Simulation, 2024, 17(12): 2145-2161.
FengCan, ShiWeiya, LiYanchao, et al. Skin lesion segmentation algorithm based on CNN and Transformer dual encoder[J]. Science Technology and Engineering, 2025, 25(23): 9900-9910.
HouYifan, XuTianqi, LiYan, et al. Data-driven transient stability assessment of power systems based on Transformer-GAT parallel feature fusion[J]. Science Technology and Engineering, 2025, 25(21): 8945-8954.
[92]
LiL, LiangC J M, LiuJ, et al. ThermoCast: a cyber-physical forecasting model for datacenters[C]// Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego: ACM, 2011: 1370-1378.
[93]
WangL, KhanS U, DayalJ. Thermal aware workload placement with task-temperature profiles in a data center[J]. The Journal of Supercomputing, 2012, 61(3): 780-803.
[94]
LiX, WenJ. Review of building energy modeling for control and operation[J]. Renewable and Sustainable Energy Reviews, 2014, 37: 517-537.
[95]
AsgariS, MirhoseiniNejadS, MoazamigoodarziH, et al. A gray-box model for real-time transient temperature predictions in data centers[J]. Applied Thermal Engineering, 2021, 185: 116319-116337.
WangFangzhou, LiuFeng, DuZhongxuan, et al. Prediction of three-dimensional temperature fields of data center based on CNN-MLP-ThermoAttention[J]. Chemical Industry and Engineering Progress, 2025. DOI: 10.16085/j.issn.1000-6613.2025-1173.
[98]
ChenD, ChuiC K, LeeP S. Adaptive physically consistent neural networks for data center thermal dynamics modeling[J]. Applied Energy, 2025, 377. DOI: 10.1016/j.apenergy.2024.124637.
[99]
MirhoseiniNejadS, BadawyG, DownD G. Holistic thermal-aware workload management and infrastructure control for heterogeneous data centers using machine learning[J]. Future Generation Computer Systems, 2021, 118: 208-218.
[100]
CaoZ, ZhouX, WuX, et al. Data center sustainability: revisits and outlooks[J]. IEEE Transactions on Sustainable Computing, 2024, 9(3): 236-248.
[101]
ZhangQ, ZengW, LinQ, et al. Deep reinforcement learning towards real-world dynamic thermal management of data centers[J]. Applied Energy, 2023, 333: 120561.
[102]
ZhouX, WangR, WenY, et al. Joint IT-facility optimization for green data centers via deep reinforcement learning[J]. IEEE Network, 2021, 35(6): 255-262.
[103]
MoazamigoodarziH, TsaiP J, PalS, et al. Influence of cooling architecture on data center power consumption[J]. Energy, 2019, 183: 525-535.
ZuoChunshuai, LiFengyong, ZhangXueyou, et al. Influence of data center cooling architecture on the cooling effect of air conditioner[J]. Journal of Building Energy Efficiency, 2024, 52(12): 101-106.
[106]
Akbari VarzanehM R, HormozinejadA, FarhaniehB. Data-driven control strategy for thermal enhancement in row-based data centers[J]. Applied Thermal Engineering, 2025, 278. DOI: 10.1016/j.applthermaleng.2025.126972.
[107]
PhanL, HuB, LinC X. An evaluation of turbulence and tile models at server rack level for data centers undefined[J]. Building and Environment, 2019, 155: 421-435.
[108]
AbbasA M, HuzayyinA S, MouneerT A, et al. Thermal mana-gement and performance enhancement of data centers architectures using aligned/staggered in-row cooling arrangements[J]. Case Studies in Thermal Engineering, 2021, 24. DOI: 10.1016/j.csite.2021.100884.
[109]
LeeY T, WenC Y, ShihY C, et al. Numerical and experimental investigations on thermal management for data center with cold aisle containment configuration[J]. Applied Energy, 2022, 307. DOI: 10.1016/j.apenergy.2021.118213.
[110]
BeitelmalA H, PatelC D. Thermo-fluids provisioning of a high performance high density data center[J]. Distributed and Parallel Databases, 2007, 21(2/3): 227-238.
HuangJinsen, ZhuBing, ZhangYiming, et al. Transient thermal parameter prediction based on SVR data center air conditioning system[J]. Intelligent Computer and Applications, 2023, 13(11): 161-165.
[113]
PatelD, JoshiY. Data driven modeling advancements for air temperature predictions in data centers[J]. Numerical Heat Transfer, Part B: Fundamentals, 2025, 86(2): 244-261.
[114]
Van DammeT, De PersisC, TesiP. Optimized thermal-aware job scheduling and control of data centers[J]. IEEE Transactions on Control Systems Technology, 2019, 27(2): 760-771.
GaoCiwei, CaoXiaojun, YanHuaguang, et al. Energy management of data center and prospect for participation in demand side resource scheduling[J]. Automation of Electric Power Systems, 2017, 41(23): 1-7.
WangBo, GuoYanhua, ShaoShuangquan, et al. Review of energy efficiency evaluation indexes related to data center cooling systems[J]. Journal of Refrigeration, 2023, 44(2): 18-27.