The Data Center Frontier Executive Roundtable features insights from industry executives with lengthy experience in the data center industry. Here’s a look at the insights from Peter Panfil of Vertiv.
PETER PANFIL, Vertiv
Peter Panfil is the Vice President of Global Power at Vertiv. He leads strategic customer development for the Power business and works to apply the latest power and control technology to proven and emerging topologies to provide the availability, scalability and efficiency levels customers demand. Approaching 30 years in critical space, he has held executive positions including VP Engineering and VP/GM AC Power prior to his current responsibilities. He is a frequent presenter and spokesperson for industry trade shows, conferences and media outlets serving the IT, facilities and engineering industry.
Here’s the full text of Peter Panfil’s insights from our Executive Roundtable:
Data Center Frontier: How is edge computing evolving, and what use cases and applications are gaining the most traction with customers?
Peter Panfil: Edge computing is an extremely versatile strategy that can be used to support a range of applications depending on where it is deployed. Vertiv has identified four edge computing models – from the device edge to the regional edge – and the applications being supported by these models, or a combination of them, can be very different.
We recently surveyed the market and found that the most popular applications being supported by micro edge sites, which we define as deployments of less than four racks, were predictive and condition-based maintenance, supply chain management, and real-time inventory management. In larger regional edge deployments, we are seeing growth in high-performance computing applications with rack densities for some sites pushing 50 kW. Where there used to be high-density pockets of IT spread around in data centers, they are now getting concentrated in liquid-cooled containers at the edge.
So, the edge is evolving in multiple ways with one common denominator – growth in both the amount of compute, and the percentage of an organization’s compute, deployed at the edge.
Data Center Frontier: Last year’s major service outages at Facebook and Amazon Web Services sharpened the focus on data center reliability. As companies embrace the benefits of cloud and hybrid IT architectures, what are the key strategies for ensuring uptime?
Peter Panfil: To meet growing demand for services, cloud operators have to balance speed-of-deployment, cost, reliability and sustainability. In some cases, infrastructure redundancy has been sacrificed to achieve lower build costs, which can backfire if downtime causes the market to lose confidence in the reliability of cloud services.
Two trends have emerged that enable operators to achieve their speed and cost goals without compromising reliability. One is value engineering of high-utilization critical power architectures that maintain redundancy while eliminating stranded capacity and maximizing efficiency. The other is the availability of modular prefabricated data centers, which can be deployed in less time than is possible using traditional construction methods while delivering extremely low PUEs and high availability.
Data Center Frontier: How would you assess the state of the data center supply chain? Are the global supply chain challenges impacting the delivery of data center capacity?
Peter Panfil: The pandemic has created disruptions in the supply chain, as has the way data centers responded to it. Many are taking a “bounce forward” approach in which they are conducting major modernization and upgrades so they can come out of this period stronger and more resilient than they went into it. That has put further pressure on the supply chain.
Vendors across the value chain are working with their customers to get ahead of supply chain issues through proactive communication, longer term project planning, and enhanced maintenance practices that extend the lifecycle of existing equipment.
Data Center Frontier: Several data center observers, including The Uptime Institute, have highlighted nuclear power as an option for data center operators to create a low-carbon energy future. Is turning to nuclear power – either through power purchase agreements or modular reactors – a viable option for the data center industry? Should it be?
Peter Panfil: We are seeing a sense of urgency around moving away from fossil fuels and enhancing data center resource utilization among many operators. We expect most to turn to renewable energy rather than nuclear power to achieve their sustainability goals. When paired with fuel cells for energy storage, the traditional UPS is morphing into an Intelligent power converter that allows the grid to provide emergency backup power.
Locally generated renewable energy presents the clearest and most cost-effective path toward a sustainable and climate-friendly future for the industry. The technologies required to support this goal are already further along than many realize, and are advancing rapidly.