Operational Data Analytics: Optimizing the National Energy Research Scientific Computing Center Cooling Systems

被引：16

作者：

Bourassa, Norman ^{[1
]}

Johnson, Walker ^{[2
]}

Broughton, Jeff ^{[1
]}

Carter, Deirdre McShane ^{[1
]}

Joy, Sadie ^{[2
]}

Vitti, Raphael ^{[2
]}

Seto, Peter ^{[3
]}

机构：

[1] Lawrence Berkeley Natl Lab, Berkeley, CA 94720 USA

[2] kW Engn Inc, New York, NY USA

[3] Energy Efficient HPC Working Grp, New York, NY USA

来源：

PROCEEDINGS OF THE 48TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING WORKSHOPS (ICPP 2019) | 2019年

关键词：

building management systems; building controls; energy efficiency; data centers; operations; high-performance computing; data collection; data analytics; time series data; Green HPC; PUE; iTUE;

D O I：

10.1145/3339186.3339210

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In 2017/2018, the Energy Efficient HPC Working Group (EE HPC WG) Dashboard Team conducted an analysis that assessed the current use of information dashboards for operational facility management in major supercomputing centers around the globe, resulting in the formalization of a process now referred to as Operational Data Analytics (ODA). Subsequent to surveys of multiple HPC facilities, the EE HPC WG determined that case studies were needed to help HPC facilities evaluate the value of implementing ODA practices. This paper provides a summary of the successful use of an ODA approach being used by the National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Laboratory (Berkeley Lab) in meeting organizational energy efficiency performance goals for the NERSC HPC cooling systems.

引用

页数：7