Colocation Data Center Success: High-Performance Computing and Energy Efficiency

It may sound counterintuitive, but even high-capacity data centers such as those that focus on high-performance computing (HPC) and artificial intelligence (AI) can also be energy efficient. We’re proud to support organizations in meeting both their performance and their sustainability goals simultaneously. One such case is our work alongside wholesale and high-performance colocation provider Kao Data. Specifically, Kao Data used Cadence data center software to validate its Indirect Evaporative Cooling (IEC) data center design. Kao Data continues to use Cadence data center software to make informed and data-driven decisions around design, implementation, and operations.

Case Study Overview

In 2018, Kao Data launched Kao Data London One (KLON-01 ). KLON-01 is the UK’s first 100% wholesale multi-tenant data center to provide 100% free cooling (i.e., with no mechanical cooling) and is designed to deliver energy-efficient colocation services for high-performance computing (HPC), artificial intelligence (AI), and enterprise organizations. The data center offers a PUE of <1.2, even at partial loads, and hyperscale levels of efficiency.

Despite its high-performance demands, environmental sustainability is still at the forefront of KLON-01 ’s design. Kao Data considered, and ultimately deployed, a refrigerant-free Indirect Evaporative Cooling (IEC) system. This uses water evaporation in place of mechanical systems to cool air on hot days, ensuring greater levels of energy efficiency.

Using Cadence data center software, Cadence engineers and Kao Data’s design consultant provided computational fluid dynamics (CFD) simulations of the internal and external data center operating environments to help Kao Data make informed, data-driven decisions around design, implementation, and operations.

Design Expectations

Kao Data’s campus was split into four data centers totaling roughly 150,000 square feet of technical space. Each facility offers a total technical load of 8.8MW, accommodating rack densities of 25kW – 40kW and beyond. From inception, the Kao Data campus was designed to cater to industrial-scale intensive computing, as well as OCP-Ready and GPU-accelerated supercomputing systems.

It is well known that GPU-intensive systems have demanding power and cooling requirements. To meet these requirements, and their sustainability goals, Kao Data knew they needed to pinpoint operational efficiency wins, employ effective power and cooling systems, and contract 100% renewable energy.

Kao Data turned to an IEC system to meet cooling requirements and work toward their sustainability goals. IECs use external air to cool the facility, without allowing external and internal airstreams to mix. It is critical in IEC design to segregate the intake and exhaust of the external air path to avoid moist air being drawn back in.

Cadence data center software was pivotal in validating and executing this technology. Cadence data center software uses CFD simulation to virtually model the internal and external data center environment and its physical operations. Kao Data needed factual data to ensure its ambitious design specifications could be achieved without putting any of its equipment at risk. Cadence data center software’s external modeling capabilities helped Kao Data manage risk and ensure industry-leading levels of efficiency, before committing to the build phase of the project.

Evaluate New Technologies and Ensure Safe Implementation

Cadence data center software creates a digital twin of the data center that can assess data center performance, such as testing different deployment scenarios and new technology implementation. Specifically, Kao Data wanted to evaluate the facility’s cooling performance under various conditions, including multiple weather scenarios, several operating conditions at full and partial utilization, and different design variations of the physical construction.

Using Cadence data center software, Kao Data was able to:

• Evaluate the viability and performance of the proposed IEC design concept
• Confirm the satisfactory cooling performance of each of the proposed build-out stages
• Demonstrate the effect of potential variations and extreme environmental conditions
• Verify that predicted IEC inlet conditions for a variety of external conditions were acceptable and should not compromise IEC performance

Kao Data studied the external data center site using Cadence’s CFD simulation to understand the design’s thermal performance under different weather conditions throughout the various stages of site build-out.

Maximize Both Operational and Energy Efficiency

“Cadence’s industry-leading reputation for CFD analysis was pivotal in helping us to design and build one of the most sustainable and energy-efficient facilities in the UK,” said Paul Finch, Chief Operating Officer (COO) at Kao Data. “It has helped us refine our decision-making process around the provision of cooling infrastructure and, more recently, was crucial in the deployment of NVIDIA’s Cambridge-1 supercomputer.”

We continue to help Kao Data deliver a highly sustainable colocation solution by modeling complex designs for enterprise, HPC, and AI customers.

Find out how Cadence data center software can help your team maximize both operational and energy efficiency and read the full Kao Data Success Story.