Grant: Collaborative Research and Development Grants
McMaster University
$238,820.00
Adaptive thermal management of data centres
FY 2018-19
Summary
The rapid growth of cloud services and high performance computing has spurred meteoric growth of their supporting physical infrastructure, known as Data Centres (DCs). While this has been facilitated by more powerful computing equipment, their cooling systems have not evolved similarly, leading to poor cooling efficiency that originates from (1) use of air as coolant despite its poor thermal properties, and (2) inability to regulate cooling capacity based on spatiotemporal changes in demand. The proposed research will create a pioneering adaptive DC cooling system that will match the spatiotemporal variations in cooling demand across a DC, thereby providing significant energy savings and reducing total cost of ownership. This development will be enabled by (1) a system that monitors a network of wireless temperature, humidity, pressure, and flow sensors for air and liquid, and CPU workload and energy consumption in real time at several locations across the facility, (2) a control system that adaptively controls cooling capacity based on sensor data, and (3) a novel family of easily controllable cooling hardware consisting of heat removal elements and thermal buses. The unique cooling system architecture proposed here will minimally impact the typical existing DC infrastructure, thereby allowing inexpensive and seamless adoption. The technology will be commercialized by our industry partner Cinnos Mission Critical Inc., adding ~116.5M new revenue stream to their product offering which will create 220+ jobs by 2021. In addition, it will make their flagship modular DC product SMC-X more competitive by improving its energy efficiency and reducing real-estate footprint. Apart from immediate commercial benefit, the project will advance scientific knowledge in additive manufacturing of heat exchangers, and structure-property relations of nanofluids. The project outcomes promise substantial environmental benefit to Canada by reducing energy consumption and developing alternative coolants with low environmental impact. Further, the development of human capital with unique and high-demand expertise in design and operation of DCs will drive the growth of the Canadian DC industry. *
Program
Collaborative Research and Development Grants
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
506144-2016
Name nom
Puri, Ishwar
Department département
Mechanical Engineering
Organization id
27
Institution établissement
McMaster University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2018
Competition year année de concours
2016
Award amount
238820
Program id
CRDPJ
Program name en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2100
Research subject group en
Mechanical engineering
Research subject group fr
Génie mécanique
Research subject en
Mechanical engineering
Research subject fr
Génie mécanique
Partie
2
Nb partie
2
Application title
Adaptive thermal management of data centres
Keyword
NSERC
Application summary
The rapid growth of cloud services and high performance computing has spurred meteoric growth of their supporting physical infrastructure, known as Data Centres (DCs). While this has been facilitated by more powerful computing equipment, their cooling systems have not evolved similarly, leading to poor cooling efficiency that originates from (1) use of air as coolant despite its poor thermal properties, and (2) inability to regulate cooling capacity based on spatiotemporal changes in demand. The proposed research will create a pioneering adaptive DC cooling system that will match the spatiotemporal variations in cooling demand across a DC, thereby providing significant energy savings and reducing total cost of ownership. This development will be enabled by (1) a system that monitors a network of wireless temperature, humidity, pressure, and flow sensors for air and liquid, and CPU workload and energy consumption in real time at several locations across the facility, (2) a control system that adaptively controls cooling capacity based on sensor data, and (3) a novel family of easily controllable cooling hardware consisting of heat removal elements and thermal buses. The unique cooling system architecture proposed here will minimally impact the typical existing DC infrastructure, thereby allowing inexpensive and seamless adoption. The technology will be commercialized by our industry partner Cinnos Mission Critical Inc., adding ~116.5M new revenue stream to their product offering which will create 220+ jobs by 2021. In addition, it will make their flagship modular DC product SMC-X more competitive by improving its energy efficiency and reducing real-estate footprint. Apart from immediate commercial benefit, the project will advance scientific knowledge in additive manufacturing of heat exchangers, and structure-property relations of nanofluids. The project outcomes promise substantial environmental benefit to Canada by reducing energy consumption and developing alternative coolants with low environmental impact. Further, the development of human capital with unique and high-demand expertise in design and operation of DCs will drive the growth of the Canadian DC industry. *