Heat to Power: Thermal Energy Harvesting and Recycling for Warm Water-Cooled Datacenters

Zhu, Xinhui; Weixiang, Jiang; Liu, Fangming; Zhang, Qixia; Li, Pan; Chen, Qiong; Jia, Ziyang

doi:10.1109/isca45697.2020.00042

Cited by 9 publications

(11 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other cooling units, such as computer room air handlers, were implemented to the CoolEmAll project by Cupertino et al [24] . Zhu et al [25] used a water- cooling system architecture to benefit from such a system to generate electricity using thermoelectric generators (TEGs) from the warm water part of the cooling system.…”

Section: Cooling Modelmentioning

confidence: 99%

“…Zheng et al [21] proposed TE-Shave, which stores inexpensive electricity at night or unstable green energy to sustain the power supply during the outage emergency using traditional UPS batteries alongside TES tanks, the latter being more actively used. Zhu et al [25] proposed an economical and energyrecycling warm water-cooling architecture, namely, Heat to Power (H2P), where TEGs harvest the thermal energy that uses warm water and generates electricity. The proposed model was utilized to build an optimization method that uses the fine-grained adjustments of the cooling setting and dynamic workload scheduling to increase the power generated by TEGs.…”

Section: Power Modelmentioning

confidence: 99%

“…The proposed model was utilized to build an optimization method that uses the fine-grained adjustments of the cooling setting and dynamic workload scheduling to increase the power generated by TEGs. The authors claimed that TEGs equipped with their optimization methods produce 4349 W, 4203 W, and 3979 W of electricity on a single CPU on average under any workload traces [25] . The power reusing performance can hit 12.8% by 16.2%, and data centers' total ownership cost can be decreased by up to 0.57%.…”

Section: Power Modelmentioning

confidence: 99%

See 2 more Smart Citations

Research advances on AI-powered thermal management for data centers

Liu

Aljbri

Song

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Given the complex nature of data centers' thermal management, which costs too many resources, processing time, and energy consumption, thermal awareness and thermal management powered by artificial intelligence (AI ) are the targeted study. In addition to a few research on AI techniques and models, other strategies have also been introduced in recent years. Data center models, including cooling, thermal, power, and workload models, and their relationship are factors that need to be understood in the optimal thermal management system.Simulation approaches have been proposed to help validate new models or methods used for scheduling and consolidating processes and virtual machines (VMs), hotspot identification, thermal state estimation, and power usage change. AI-powered thermal optimization leads to improved process scheduling and consolidation of VMs and eliminates the hotspot from happening. At present, research on AI-powered thermal control is still in its infancy. This paper concludes with four issues in thermal management, which will be the scope of further research.

show abstract

Section: Cooling Modelmentioning

confidence: 99%

Section: Power Modelmentioning

confidence: 99%

Section: Power Modelmentioning

confidence: 99%

See 1 more Smart Citation

Research advances on AI-powered thermal management for data centers

Liu

Aljbri

Song

et al. 2022

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Currently, warm water cooling (e.g., 40℃∼50℃) emerges to reduce cooling costs by avoiding over-cooling servers running at a low utilization and allowing less or even no use of the chiller [41,118].…”

Section: Introductionmentioning

confidence: 99%

“…To cool down even a small portion of hotspot hardware components for their safety, the inlet water for every hardware component should be chilled to a very low temperature synchronously. This over-provisioning strategy is exceedingly inefficient since the centralized chiller needs to consume extra energy to provide cold water to other non-hotspots at the same time [41,100,118]. One possible solution might be installing distributed chillers or pumps for each hardware component, but the high costs, additional space demands, and other technical problems make this infeasible [19,41].…”

Section: Introductionmentioning

confidence: 99%

CoolEdge: hotspot-relievable warm water cooling for energy-efficient edge datacenters

Pei

Chen

Zhang

et al. 2022

Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems

Self Cite

View full text Add to dashboard Cite

As the computing frontier drifts to the edge, edge datacenters play a crucial role in supporting various real-time applications. Different from cloud datacenters, the requirements of proximity to end-users, high density, and heterogeneity, present new challenges to cool the edge datacenters efficiently. Although warm water cooling has become a promising cooling technique for this infrastructure, the one-size-fits-all cooling control would lower the cooling efficiency considerably because of the severe thermal imbalance across servers, hardware, and even inside one hardware component in an edge datacenter. In this work, we propose CoolEdge, a hotspot-relievable warm water cooling system for improving the cooling efficiency and saving costs of edge datacenters. Specifically, through the elaborate design of water circulations, CoolEdge can dynamically adjust the water temperature and flow rate for each heterogeneous hardware component to eliminate the hardwarelevel hotspots. By redesigning cold plates, CoolEdge can quickly disperse the chip-level hotspots without manual intervention. We further quantify the power saving achieved by the warm water

show abstract

Heat Wave Resilient Systems Architecture for Underwater Data Centers

Periola

Alonge

Ogudo

2022

Sci Rep

View full text Add to dashboard Cite

The need to design computing platforms with low water footprint and enhanced energy efficiency makes non-terrestrial computing platforms attractive. Large scale computing platforms in non-terrestrial environments are increasingly receiving attention. In this regard, underwater data centers (UDCs) are considered to have operational benefits due to their low cooling cost. Underwater data centers experience challenges due to marine heat waves. The occurrence of marine heat waves limits the amount of ocean water available for UDC cooling. This paper proposes a mechanism to detect marine heat waves, and ensure continued UDC functioning. The proposed mechanism utilizes reservoirs to store water and ensure continued functioning of underwater data center. In addition, the proposed research presents the reservoir as a service (RaaS) for ensuring UDC cooling. Furthermore, the presented research also describes modular form factor approach for UDC development. This is being done with the aim of enhancing UDC adoption and use in capital constrained contexts. The underwater data center operational duration is investigated. Evaluation shows that the proposed solution enhances the operational duration by an average of (5.5–12.3) % and (5.2–11.5) % given that marine heat waves span 10 epochs and 15 epochs during an operational phase, respectively.

show abstract

Heat to Power: Thermal Energy Harvesting and Recycling for Warm Water-Cooled Datacenters

Cited by 9 publications

References 32 publications

Research advances on AI-powered thermal management for data centers

Research advances on AI-powered thermal management for data centers

CoolEdge: hotspot-relievable warm water cooling for energy-efficient edge datacenters

Heat Wave Resilient Systems Architecture for Underwater Data Centers

Contact Info

Product

Resources

About