4.7 Article

A time-varying state-space model for real-time temperature predictions in rack-based cooling data centers

Related references

Note: Only part of the references are listed.
Article Green & Sustainable Science & Technology

Research and Technologies for next-generation high-temperature data centers-State-of-the-arts and future perspectives

Yingbo Zhang et al.

Summary: Data centers have attracted worldwide attention due to their high energy consumption, and high-temperature data centers could save significant cooling energy. However, addressing technical bottlenecks and ensuring equipment reliability are essential before implementing high-temperature data centers. This paper provides a comprehensive review of these critical aspects, categorizing and analyzing the benefits, bottlenecks, and potential solutions.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2023)

Article Construction & Building Technology

Calibration method for sensor drifting bias in data center cooling system using Bayesian Inference coupling with Autoencoder

Yaoyue Tian et al.

Summary: This study proposed a novel method based on Bayesian inference coupled with autoencoder to calibrate the drifting bias of sensors in data center cooling supply systems. Case studies were conducted to evaluate the calibration performance of the proposed method, and the simulation results show that it performs well in terms of correction accuracy. The study fills the knowledge gap in sensor drifting bias correction for data centers and facilitates the application of advanced technologies.

JOURNAL OF BUILDING ENGINEERING (2023)

Article Construction & Building Technology

In-situ sensor correction method for data center cooling systems using Bayesian Inference coupling with autoencoder

Jiaqiang Wang et al.

Summary: This study proposed a novel sensor correction method for data center cooling systems using Bayesian Inference and autoencoder. The method showed excellent correction accuracy in different sensor error scenarios, and the accuracy was influenced by the system model.

SUSTAINABLE CITIES AND SOCIETY (2022)

Article Thermodynamics

Experimental analysis of airflow uniformity and energy consumption in data centers

Yogesh Fulpagare et al.

Summary: This research study investigates temperature and airflow uniformity, as well as energy consumption, in a small data center. The study found that using 50% porous tiles in partial containment provided the best airflow and temperature uniformity.

APPLIED THERMAL ENGINEERING (2022)

Article Thermodynamics

Thermal prediction for Air-cooled data center using data Driven-based model

Jianpeng Lin et al.

Summary: This study compares the temperature prediction performance of six machine learning-based thermal models in steady-state and transient-state scenarios. The results show that the XGBoost-based and LightGBM-based models outperform other ML models in both scenarios, with high adaptability.

APPLIED THERMAL ENGINEERING (2022)

Article Thermodynamics

Experimental study on reliable operation strategy for multi-split backplane cooling system in data centers

Xiuming Li et al.

Summary: The reason for cooling failure in the multi-split backplane cooling system in data centers under lower outside ambient temperature is explored, and a reliable operation control strategy is proposed to save energy consumption.

APPLIED THERMAL ENGINEERING (2022)

Article Energy & Fuels

Energy, exergy and computing efficiency based data center workload and cooling management

Rohit Gupta et al.

Summary: This study presents a new approach to optimize workload distribution in multi-rack data centers by considering coefficient of performance, exergy efficiency, and computing performance. The findings reveal the physics behind two-dimensional workload management in multi-rack data centers and provide a framework for balancing trade-offs between different objectives.

APPLIED ENERGY (2021)

Review Thermodynamics

A state-of-the-art review on the application of heat pipe system in data centers

Li Ling et al.

Summary: Data centers have been increasing in number and size due to the rapid development in demand for data storage, networking, and computation. A heat pipe system is considered a promising solution to reduce the energy consumption of cooling systems, with high thermal efficiency, reliability, and cost effectiveness. This study provides a systematic review of existing heat pipe systems applied in data centers, focusing on types, thermal characteristics analysis, and energy efficiency comparison.

APPLIED THERMAL ENGINEERING (2021)

Article Computer Science, Theory & Methods

Hybrid surrogate model for online temperature and pressure predictions in data centers

Sahar Asgari et al.

Summary: The study focuses on the issues in data center design and operation, and develops a hybrid surrogate model to accurately predict temperature distribution within a data center. By combining data-driven models and thermofluid transport relations, more effective optimization of airflow distribution, reduced energy consumption, and improved cooling configuration design in data centers can be achieved.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2021)

Article Thermodynamics

A gray-box model for real-time transient temperature predictions in data centers

Sahar Asgari et al.

Summary: This article discusses the use of solutions such as continuous performance monitoring, automated diagnostics, and optimal control to improve the energy efficiency of data centers. A gray-box model that combines machine learning with thermofluid transport equations is developed to predict transient temperatures in server CPUs and cold air inlet to the servers, showing superior performance compared to other models in predicting temperatures and detecting cooling unit fan failures in a row-based DC cooling system.

APPLIED THERMAL ENGINEERING (2021)

Article Automation & Control Systems

Adaptive Predictive Control of a data center cooling unit

Fernando Martinez-Garcia et al.

Summary: As server densities increase, traditional room cooling infrastructure struggles to keep up with demand, leading to the deployment of rack-mounted cooling units in data centers. This study implements a Multi-Input Single-Output Adaptive Predictive Controller using a low-cost microcontroller, which outperforms standard controllers in simulations.

CONTROL ENGINEERING PRACTICE (2021)

Article Automation & Control Systems

Data-driven fault tolerant predictive control for temperature regulation in data center with rack-based cooling architecture

Kai Jiang et al.

Summary: This paper investigates an efficient cooling architecture named RMCU and a novel data-driven fault tolerant predictive controller to regulate the temperature in data centers. A data-driven modeling method is developed using ARX models to describe the system and PLS and FCM to identify sub-models and partition training data. A predictive controller considering actuator faults is designed, demonstrating superior performance in managing temperature in data centers through real experimental results.

MECHATRONICS (2021)

Article Computer Science, Theory & Methods

Holistic thermal-aware workload management and infrastructure control for heterogeneous data centers using machine learning

SeyedMorteza MirhoseiniNejad et al.

Summary: This paper investigates the energy consumption of IT equipment and cooling infrastructures in data centers, proposing a holistic data center infrastructure control (HDIC) method to save a considerable amount of power by optimizing the synergies between workload scheduler and operational parameters of cooling units.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2021)

Article Computer Science, Theory & Methods

Joint data center cooling and workload management: A thermal-aware approach

SeyedMorteza MirhoseiniNejad et al.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2020)

Editorial Material Multidisciplinary Sciences

Recalibrating global data center energy-use estimates

Eric Masanet et al.

SCIENCE (2020)

Review Energy & Fuels

A review of power consumption models of servers in data centers

Chaoqiang Jin et al.

APPLIED ENERGY (2020)

Article Automation & Control Systems

Temperature distribution estimation via data-driven model and adaptive Kalman filter in modular data centers

Kai Jiang et al.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING (2020)

Article Thermodynamics

Performance of a rack mountable cooling unit in an IT server enclosure

Hosein Moazamigoodarzi et al.

THERMAL SCIENCE AND ENGINEERING PROGRESS (2020)

Article Thermodynamics

Numerical and experimental investigations on the thermal performance of a data center

Hongjie Lu et al.

APPLIED THERMAL ENGINEERING (2020)

Article Thermodynamics

Modular modeling of air-conditioning system with state-space method and graph theory

Ye Yao et al.

INTERNATIONAL JOURNAL OF REFRIGERATION-REVUE INTERNATIONALE DU FROID (2019)

Article Construction & Building Technology

The study of servers' arrangement and air distribution strategy under partial load in data centers

Chaoqiang Jin et al.

SUSTAINABLE CITIES AND SOCIETY (2019)

Article Thermodynamics

Comparison of data driven modeling approaches for temperature prediction in data centers

Jayati Athavale et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2019)

Article Thermodynamics

Influence of cooling architecture on data center power consumption

Hosein Moazamigoodarzi et al.

ENERGY (2019)

Article Construction & Building Technology

Impact of uncertainties on the supervisory control performance of a hybrid cooling system in data center

Jiaqiang Wang et al.

BUILDING AND ENVIRONMENT (2019)

Article Automation & Control Systems

Data centre adaptive numerical temperature models

Vassilios A. Tsachouridis et al.

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL (2018)

Article Automation & Control Systems

Identification of structured state-space models

Chengpu Yu et al.

AUTOMATICA (2018)

Article Automation & Control Systems

An optimized active disturbance rejection approach to fan control in server

Qinling Zheng et al.

CONTROL ENGINEERING PRACTICE (2018)

Article Thermodynamics

Real-time temperature predictions in IT server enclosures

Hosein Moazamigoodarzi et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2018)

Article Computer Science, Artificial Intelligence

Runtime data center temperature prediction using Grammatical Evolution techniques

Marina Zapater et al.

APPLIED SOFT COMPUTING (2016)

Article Thermodynamics

A hybrid lumped capacitance-CFD model for the simulation of data center transients

Hamza Salih Erden et al.

HVAC&R RESEARCH (2014)

Article Construction & Building Technology

A state-space model for dynamic response of indoor air temperature and humidity

Ye Yao et al.

BUILDING AND ENVIRONMENT (2013)