The Importance of Measuring Data Center Performance and How to Get Started

Aug. 18, 2023
Sherman Ikemoto, System Sales Group Director at Cadence, explains the importance of measuring data center performance and how operators can begin to tackle efficiency using science-backed methodology.
There’s much more to data center operations than managing the environment for safe operation of the IT configuration. Data center operators are increasingly tasked with running their data centers as efficiently as possible.
The word “efficiently” is used quite often in the data center industry, but efficient in terms of what? Deployment speed? Energy? Cost?

The answer depends on whom you ask. To upper management, the answer is likely all of the above. In this article, I’d like to discuss the importance of measuring data center performance and how operators can begin to tackle “all of the above” by using a quantifiable, science-backed methodology.

Competing Demands Exacerbate Data Center Performance Issues

Data center operators are regularly tasked with delivering more processing throughput in less space in a sustainable fashion. This is easier said than done when considering the conflicting demands facing operators.

The proliferation of high-performance applications and high-density IT equipment increases pressure on the data center system. Mixed-density IT equipment can create demands for power and cooling resources that facilities—especially legacy facilities—are unable to accommodate. Adding to this challenge is the fact that current data center management tools and techniques lack the ability to predict the impact of operational changes, such as deploying high-density IT hardware, on the data center’s ability to power and cool the IT configuration. This can leave operators with no choice but to overcompensate on resource provisions to counteract this risk.

In turn, overcompensating on these resources can negatively impact carbon emissions and energy costs. Sustainability regulations, such as the Energy Efficiency Directive, are on the horizon. These regulations will place additional pressure on operators to track, report, and inevitably reduce power and cooling provisions without increasing the risk of power- or cooling-related failures. Given these competing demands, how should operators approach the delicate balancing act that is data center performance?

Some teams will suggest focusing on space usage improvements, while others will be more concerned about the longevity of IT equipment, the carbon footprint, the OpEx, and the list goes on. The best way to understand which of these competing demands to tackle first is to measure the data center’s performance. Doing so illuminates which concerns are having the greatest impact, as well as the interconnected relationship between each demand.

We’ve found great success using The Green Grid’s Performance Indicator (PI) plus computational fluid dynamics (CFD) simulation to measure and improve data center performance.

How to Measure Data Center Performance

The Green Grid’s PI quantifies data center efficiency and the ability to meet IT cooling requirements. This provides a balanced understanding of data center performance and addresses how conflicting data center performance metrics impact one another. CFD simulation models complex thermals and cooling, which operators can use to validate operational decisions virtually before physical implementation.

The Green Grid’s PI helps visualize the balance between achieving effective cooling during normal operation (IT Thermal Conformance) and adequate cooling during failure or maintenance within design parameters (IT Thermal Resilience), without compromising efficiency (PUE ratio), illustrated in the figure below.

The Green Grid’s PI considers the future effect of proposed changes before implementation of IT deployments. This methodology, plus CFD simulation, can provide a more complete understanding of the impact layout changes will have on operations.

With each new deployment, a data center’s layout changes from the original design. Even with the same total cooling, two different layouts can produce drastically different performance results. Using The Green Grid’s PI and a CFD-powered data center digital twin, operators can plan, test, and validate operational changes before physical implementation, while also considering sustainability metrics.

Measure, Test, and Improve Data Center Performance

Small, targeted adjustments to data center operations can have a significant impact on utilizing data center space effectively while working towards greater energy efficiency. Discovering these adjustments starts with measuring data center performance.

Measuring data center performance is easier and more effective when using a quantifiable methodology, such as The Green Grid’s PI, and science-backed data, like CFD simulation. When done correctly, a performance assessment is the first step toward understanding how to balance the conflicting parameters of data center performance.

Sherman Ikemoto is System Sales Group Director at Cadence Design Systems. Contact Cadence to learn more. 

About the Author

Voices of the Industry

Our Voice of the Industry feature showcases guest articles on thought leadership from sponsors of Data Center Frontier. For more information, see our Voices of the Industry description and guidelines.

Sponsored Recommendations

The AI Disruption: Challenges and Guidance for Data Center Design

From large training clusters to small edge inference servers, AI is becoming a larger percentage of data center workloads. Learn more.

A better approach to boost data center capacity – Supply capacity agreements

Explore a transformative approach to data center capacity planning with insights on supply capacity agreements, addressing the impact of COVID-19, the AI race, and the evolving...

How Modernizing Aging Data Center Infrastructure Improves Sustainability

Explore the path to improved sustainability in data centers by modernizing aging infrastructure, uncovering challenges, three effective approaches, and specific examples outlined...

How Modern DCIM Helps Multi-Tenant Colocation Data Centers Be More Competitive

Discover the transformative impact of modern DCIM software on multi-tenant colocation data centers, enhancing competitiveness through improved resiliency, security, environmental...

Shutterstock, courtesy of Stream Data Centers

Why Liquid Cooling is More Sustainable

Stuart Lawrence of Stream Data Centers explains that because liquid is a more efficient means of heat transfer than air, liquid cooling will be necessary to support the next generation...

White Papers

Mgk Dcf Wp Cover1 2023 01 09 10 34 33

Data Center Microgrids: The Case for Microgrids at Data Centers

Jan. 9, 2023
Many of the systems that businesses and the public rely on in the modern world are dependent on the internet, making data centers a critical form of infrastructure. But as the...