A survey on data center cooling systems: Technology, power consumption modeling and control strategy optimization

Zhang, Qingxia; Meng, Zihao; Hong, Xianwen; Zhan, Yuhao; Liu, Jia; Dong, Jiabao; Bai, Tian; Niu, Junyu; Deen, M. Jamal

doi:10.1016/j.sysarc.2021.102253

Cited by 120 publications

(30 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under such a layout, heat recirculation will be prevented to a large extent. For other data hall air flow management techniques with air cooling such as in-rack cooling, please refer to [109] for detailed discussion. Moreover, data center operators can also choose cooling systems with higher energy efficiency such as liquid cooling systems [110] to achieve further cooling energy reduction.…”

Section: Air-side Economizermentioning

confidence: 99%

“…Since liquid has much higher specific heat capacity than air, liquid cooling has superior cooling efficiency and is suitable for future data centers with growing energy density. As for the liquid cooling system, it can be classified into direct liquid cooling and indirect liquid cooling [109]. Direct liquid cooling means that dielectric liquid coolant contacts the electronic devices directly to absorb heat dissipated by them, e.g., immsersion cooling [111].…”

Section: Air-side Economizermentioning

confidence: 99%

See 1 more Smart Citation

Toward a Systematic Survey for Carbon Neutral Data Centers

Cao

Zhou

et al. 2022

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Section: Air-side Economizermentioning

confidence: 99%

Section: Air-side Economizermentioning

confidence: 99%

Toward a Systematic Survey for Carbon Neutral Data Centers

Cao

Zhou

et al. 2022

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

“…DDC methods have to date been applied to a number of industries and applications, including power electronics [63], [83], [84], data center cooling [85], [86] and UAVs [87]- [89], amongst others.…”

Section: ) Learning-based Data-driven Controlmentioning

confidence: 99%

Toward Data-Driven Optimal Control: A Systematic Review of the Landscape

2022

View full text Add to dashboard Cite

This literature review extends and contributes to research on the development of data-driven optimal control. Previous reviews have documented the development of model-based and data-driven control in isolation and have not critically reviewed reinforcement learning approaches for adaptive data-driven optimal control frameworks. The presented review discusses the development of model-based to model-free adaptive controllers, highlighting the use of data in control frameworks. In data-driven control frameworks, reinforcement learning methods may be used to derive the optimal policy for dynamical systems. Attractive characteristics of these methods include not requiring a mathematical model of complex systems, their inherent adaptive control capabilities, being an unsupervised learning technique and their decision-making abilities, which are both an advantage and motivation behind this approach. This review considers previous reviews on these topics, including recent work on data-driven control methods. In addition, this review shows the use of data to derive system dynamics, determine the control policy using feedback information, and tune fixed controllers. Furthermore, the review summarises various data-driven methods and their corresponding characteristics. Finally, the review provides a taxonomy, a timeline and a concise narrative of the development of model-based to model-free data-driven adaptive control and underlines the limitations of these techniques due to the lack of theoretical analysis. Areas of further work include theoretical analysis on stability and robustness for data-driven control systems, explainability of black-box policy learning techniques and an evaluation of the impact of the extension of system simulators to include digital twins.INDEX TERMS Data-driven control, adaptive control, model-free, model-based, model predictive control, optimal control, learning-based control, systematic review. A. CONTINUOUS-TIME AND DISCRETE-TIME CONTROL SYSTEMSBased on whether the signal used in a control system is continuous or discrete determines whether the control system is a continuous-time or discrete-time system. A continuoustime control system has all the system's variables defined as a function of time. Conversely, if the system variables are defined at distinct discrete-time steps, then the system is a discrete-time control system [8].

show abstract

“…However, research in cloud computing largely follows two paths. The first is designing mechanisms to enhance cloud-based applications have improved quality of service 16 – 18 and designing power-efficient data centre cooling systems 19 , 20 . A review of existing work in cloud computing platforms application with relations to environmental biodiversity is in Table 1 .…”

Section: Background Workmentioning

confidence: 99%

Networked computing systems for bio-diversity and environmental preservation

Periola

Alonge

Ogudo

2022

Sci Rep

View full text Add to dashboard Cite

Computing platforms have a high water footprint that poses threat to biodiversity preservation. The high water footprint reduces water availability for habitat preservation. Hence, approaches that reduce the water footprint are needful. The presented research proposes an approach that reduces the need for water in future computing platforms. It proposes a hybrid computing platform that comprises terrestrial and non-terrestrial computing platforms. The performance benefit of using hybrid computing platforms is evaluated using the novel water potential metric. The water potential (WP) quantifies the need for water (for cooling) by computing platforms. A low WP shows that computing platforms have reduced the need for water and indicates better performance than a high WP from the perspective of reducing water footprint. Evaluation is done via performance formulation and stochastic simulation of the WP metric. Analysis shows that using the hybrid computing platform instead of the existing approach that utilizes only water-cooled terrestrial data centres reduces the WP by (4.9–93) % on average.

show abstract

A survey on data center cooling systems: Technology, power consumption modeling and control strategy optimization

Cited by 120 publications

References 81 publications

Toward a Systematic Survey for Carbon Neutral Data Centers

Toward a Systematic Survey for Carbon Neutral Data Centers

Toward Data-Driven Optimal Control: A Systematic Review of the Landscape

Networked computing systems for bio-diversity and environmental preservation

Contact Info

Product

Resources

About