Survey on AI-Based Predictive Cooling in Data Centers and Edge Devices
Main Article Content
Abstract
Increasing energy consumption and thermal concentration in current data centers and thermal power systems necessitates a high level of cooling technologies and intelligent control measures in these systems to attain efficiency, reliability and sustainability. Modern data center cooling systems are covered in this paper. These systems include liquid, air, immersion, spray, and hybrid options. Optimization techniques offered include PID control, model predictive control, and reinforcement learning. Plus, it delves into how ML, DL, and RL (reinforcement learning) may revolutionize cooling prediction, real-time adaptability, and energy optimization. The article also delves into the topic of parameter control in thermochemical treatment processes, including gasification, combustion, and pyrolysis, covering topics like the impact of pressure, heating rate, residence time, and temperature on performance and energy output. The paper illuminates both AI-based and data-based solutions to the better thermal management, emissions cuts, stronger robustness, and sustainable operation.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
References
[1] S. Garg, “Next-Gen Smart City Operations with AIOps & IoT : A Comprehensive look at Optimizing Urban Infrastructure,” J. Adv. Dev. Res., vol. 12, no. 1, 2021, doi: 10.5281/zenodo.15364012.
[2] S. Dodda, N. Kamuni, P. Nutalapati, and J. R. Vummadi, “Intelligent Data Processing for IoT Real-Time Analytics and Predictive Modeling,” in 2025 International Conference on Data Science and Its Applications (ICoDSA), IEEE, Jul. 2025, pp. 649–654. doi: 10.1109/ICoDSA67155.2025.11157424.
[3] D. Patel and R. Tandon, “Cryptographic Trust Models and Zero-Knowledge Proofs for Secure Cloud Access Control and Authentication,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 2, no. 1, pp. 749–758, Dec. 2022, doi: 10.48175/IJARSCT-7744D.
[4] F. C. Andriulo, M. Fiore, M. Mongiello, E. Traversa, and V. Zizzo, “Edge Computing and Cloud Computing for Internet of Things: A Review,” Informatics, vol. 11, no. 4, 2024, doi: 10.3390/informatics11040071.
[5] K. M. R. Seetharaman, “Internet of Things (IoT) Applications in SAP: A Survey of Trends, Challenges, and Opportunities,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 3, no. 2, Mar. 2021, doi: 10.48175/IJARSCT-6268B.
[6] G. Maddali, “An Efficient Bio-Inspired Optimization Framework for Scalable Task Scheduling in Cloud Computing Environments,” Int. J. Curr. Eng. Technol., vol. 15, no. 3, 2025.
[7] R. Patel and R. Tandon, “Advancements in Data Center Engineering: Optimizing Thermal Management, HVAC Systems, and Structural Reliability,” Int. J. Res. Anal. Rev., vol. 8, no. 2, 2021.
[8] R. Patel, “Optimizing Communication Protocols in Industrial IoT Edge Networks: A Review of State-of-the-Art Techniques,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 4, no. 19, pp. 503–514, May 2023, doi: 10.48175/IJARSCT-11979B.
[9] G. Sarraf, “Resilient Communication Protocols for Industrial IoT : Securing Cyber- Physical-Systems at Scale,” Int. J. Curr. Eng. Technol., vol. 11, no. 6, pp. 694–702, 2021, doi: 10.14741/ijcet/v.11.6.14.
[10] P. B. Patel, “Energy Consumption Forecasting and Optimization in Smart HVAC Systems Using Deep Learning,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 4, no. 3, pp. 780–788, 2024, doi: 10.48175/IJARSCT-18991.
[11] A. Kula, D. Dąbrowski, M. Blachnik, M. Sajkowski, A. Smalcerz, and Z. Kamiński, “Modelling the Temperature of a Data Centre Cooling System Using Machine Learning Methods,” Energies, vol. 18, no. 10, 2025, doi: 10.3390/en18102581.
[12] T. Maggos et al., “Improvement of Buildings’ Air Quality and Energy Consumption Using Air Purifying Paints,” Appl. Sci., vol. 14, no. 14, 2024, doi: 10.3390/app14145997.
[13] Y. Gebreyesus, D. Dalton, D. De Chiara, M. Chinnici, and A. Chinnici, “AI for Automating Data Center Operations: Model Explainability in the Data Centre Context Using Shapley Additive Explanations (SHAP),” Electronics, vol. 13, no. 9, 2024, doi: 10.3390/electronics13091628.
[14] Q. Chang, Y. Huang, K. Liu, X. Xu, Y. Zhao, and S. Pan, “Optimization Control Strategies and Evaluation Metrics of Cooling Systems in Data Centers: A Review,” Sustainability, vol. 16, no. 16, 2024, doi: 10.3390/su16167222.
[15] T. Zhang et al., “Advanced Study of Spray Cooling: From Theories to Applications,” Energies, vol. 15, no. 23, 2022, doi: 10.3390/en15239219.
[16] H. Chen and D. Li, “Current Status and Challenges for Liquid-Cooled Data Centers,” Front. Energy Res., vol. Volume 10, 2022, doi: 10.3389/fenrg.2022.952680.
[17] P. B. Patel, “Predictive Maintenance in HVAC Systems Using Machine Learning Algorithms: A Comparative Study,” Int. J. Eng. Sci. Math., vol. 13, no. 12, 2024.
[18] Y. Zhang, C. Fan, and G. Li, “Discussions of Cold Plate Liquid Cooling Technology and Its Applications in Data Center Thermal Management,” Front. Energy Res., vol. Volume 10-2022, 2022, doi: 10.3389/fenrg.2022.954718.
[19] L. Xu, S. Jin, W. Ye, Y. Li, and J. Gao, “A Review of Machine Learning Methods in Turbine Cooling Optimization,” Energies, vol. 17, no. 13, 2024, doi: 10.3390/en17133177.
[20] M. R. R. Deva and N. Jain, “Utilizing Azure Automated Machine Learning and XGBoost for Predicting Cloud Resource Utilization in Enterprise Environments,” in 2025 International Conference on Networks and Cryptology (NETCRYPT), IEEE, May 2025, pp. 535–540. doi: 10.1109/NETCRYPT65877.2025.11102235.
[21] Y. Macha and S. K. Pulichikkunnu, “A Survey of DevOps Practices for Machine Learning and Artificial Intelligence Workflows in Modern Software Development,” ESP J. Eng. Technol. Adv., vol. 4, no. 3, pp. 200–208, 2024, doi: 10.56472/25832646/JETA-V4I3P121.
[22] V. Pal, “Hybrid Quantum-Classical Machine Learning Architectures for Accelerated Drug Discover,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 6, no. 2, pp. 1641–1653, 2021, doi: 10.48175/IJARSCT-6582M.
[23] P. Chandrashekar, “Data-Driven Loan Default Prediction : Enhancing Business Process Workflows with Machine Learning,” Int. J. Emerg. Res. Eng. Technol., vol. 6, no. 4, pp. 18–26, 2025.
[24] V. Verma, “Deep Learning-Based Fraud Detection in Financial Transactions : A Case Study Using Real-Time Data Streams,” vol. 3, no. 4, pp. 149–157, 2023, doi: 10.56472/25832646/JETA-V3I8P117.
[25] S. Amrale, “Anomaly Identification in Real-Time for Predictive Analytics in IoT Sensor Networks using Deep,” Int. J. Curr. Eng. Technol., vol. 14, no. 6, pp. 526–532, 2024, doi: 10.14741/ijcet/v.14.6.15.
[26] R. Bagwe, J. Kachhia, A. Erdogan, and K. George, “Automated Radar Signal Analysis Based on Deep Learning,” in 2020 10th Annual Computing and Communication Workshop and Conference (CCWC), 2020, pp. 215–221. doi: 10.1109/CCWC47524.2020.9031240.
[27] R. P. Mahajan, “Optimizing Pneumonia Identification in Chest X-Rays Using Deep Learning Pre-Trained Architecture for Image Reconstruction in Medical Imaging,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 5, no. 1, pp. 52–63, Apr. 2025, doi: 10.48175/IJARSCT-24808.
[28] K. Mphahlele, R. H. Matjie, and P. O. Osifo, “Thermodynamics, kinetics and thermal decomposition characteristics of sewage sludge during slow pyrolysis,” J. Environ. Manage., vol. 284, p. 112006, Apr. 2021, doi: 10.1016/j.jenvman.2021.112006.
[29] M. Khamies, S. Kamel, M. H. Hassan, and M. F. Elnaggar, “A Developed Frequency Control Strategy for Hybrid Two-Area Power System with Renewable Energy Sources Based on an Improved Social Network Search Algorithm,” Mathematics, vol. 10, no. 9, 2022, doi: 10.3390/math10091584.
[30] S. G. Nnabuife, J. Ugbeh-Johnson, N. E. Okeke, and C. Ogbonnaya, “Present and Projected Developments in Hydrogen Production: A Technological Review,” Carbon Capture Sci. Technol., vol. 3, p. 100042, Jun. 2022, doi: 10.1016/j.ccst.2022.100042.
[31] A. B. H. Trabelsi, K. Zaafouri, A. Friaa, S. Abidi, S. Naoui, and F. Jamaaoui, “Municipal sewage sludge energetic conversion as a tool for environmental sustainability: production of innovative biofuels and biochar,” Environ. Sci. Pollut. Res., vol. 28, no. 8, pp. 9777–9791, 2021, doi: 10.1007/s11356-020-11400-z.
[32] R. C. Brown, “The Role of Pyrolysis and Gasification in a Carbon Negative Economy,” Processes, vol. 9, no. 5, 2021, doi: 10.3390/pr9050882.
[33] J.-H. Kim, J.-I. Oh, J. Lee, and E. E. Kwon, “Valorization of sewage sludge via a pyrolytic platform using carbon dioxide as a reactive gas medium,” Energy, vol. 179, pp. 163–172, Jul. 2019, doi: 10.1016/j.energy.2019.05.020.
[34] H. P. Jagtap, A. K. Bewoor, R. Kumar, M. H. Ahmadi, and L. Chen, “Performance analysis and availability optimization to improve maintenance schedule for the turbo-generator subsystem of a thermal power plant using particle swarm optimization,” Reliab. Eng. Syst. Saf., vol. 204, p. 107130, Dec. 2020, doi: 10.1016/j.ress.2020.107130.
[35] S. Rinaldi, S. Dello Iacono, P. Bellagente, and M. Pasetti, “Analysis of Time Synchronization Challenges in Digital Twins for Edge-Enabled Data Centers in Smart Cities Scenario,” in 2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP), 2025, pp. 506–511. doi: 10.1109/PDP66500.2025.00078.
[36] L. Chen, X. Li, K. Wang, and X. Yu, “An Integrated Feature Selection and Deep Learning Method for Energy Efficiency Prediction in Data Center Cooling Systems,” in 2025 IEEE 14th Data Driven Control and Learning Systems (DDCLS), 2025, pp. 159–164. doi: 10.1109/DDCLS66240.2025.11065957.
[37] K. E. See et al., “Exploration on Miniaturization of Immersion Cooling Technology for Client Desktop and Edge Devices,” in 2024 IEEE 40th International Electronics Manufacturing Technology (IEMT), 2024, pp. 1–5. doi: 10.1109/IEMT61324.2024.10875284.
[38] D. Mebratu, B. Wondimu, R. Desai, G. Chaudhary, C. Winkel, and M. Hossain, “Liquid Cooling Pipeline Leakage Prediction and Detection using Reinforcement Learning,” in 2023 22nd IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm), 2023, pp. 1–6. doi: 10.1109/ITherm55368.2023.10177565.
[39] C. Chen et al., “A Novel Scalable Modular Immersion Cooling System Architecture for Sustainable Data Center,” in 2023 22nd IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm), 2023, pp. 1–7. doi: 10.1109/ITherm55368.2023.10177547.
[40] L. Guo et al., “A Novel Outdoor Edge Server Design with Hybrid Air Cooling and Refrigeration,” in 2022 21st IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (iTherm), 2022, pp. 1–5. doi: 10.1109/iTherm54085.2022.9899539.