How Today’s Data Centers Can Improvise, Adapt, and Overcome
A recent report by Berkeley Lab entitled, “United States Data Center Energy Usage Report,” the first comprehensive energy analysis of data centers in nearly a decade, notes that while large, hyperscale data centers are operating more efficiently, smaller data centers, which are expected to account for 60 percent of all data center energy use in 2020, remain largely inefficient.
Learning from Hyperscale Data Centers
Straining at the yoke of ever-escalating energy prices, hyperscale data centers have adopted a number of policies to become more energy efficient. For one, many no longer blast air conditioning indiscriminately to cool equipment. Instead, they’ve adopted far less energy intensive cooling strategies, like hot aisle isolation, economizers, and liquid cooling.
Another strategy is the implementation of power management software, which allows servers to scale back on their power consumption when they go into idle mode or run at less than full capacity. Still another strategy is to consolidate servers so that fewer run at higher capacities—instead of three servers running at 10 percent, run one at 30 percent. The move towards virtualization has given rise to cloud services, which has opened up a new road to energy efficiency. What also happens is that servers in small data centers are being relocated to hyperscale facilities to leverage greater energy savings.
Meeting of the Minds
What many hyperscale data centers have come to realize (and many smaller data centers have painfully grown aware of) is that achieving real energy savings calls for a coordinated effort. The coordination needs to bridge the design, implementation and operational phases with a common tool to properly manage a facility’s power draw. Conversely, the operations team may be more aware of how to properly manage a facility’s power draw.
To achieve any meaningful results, these two entities need to come together and lay out a plan that includes shutting down idle servers, improve cooling efficiencies, work out consolidation schedules and eventually look into moving some storage to the cloud. Times have changed, but the goal of efficient power management has not. Fortunately, a new breed of software management tools has emerged to help data centers meet the challenges of the next decade and beyond.
Next Generation DCIM Software Rises to the Occasion
Innovative new tools like Tuangru’s RAMP DCIM management software prove that necessity is the mother of invention. A windfall for data center operators, the software improves operations and has proven invaluable in infrastructure planning and design. It replaces Excel, Visio, and homegrown solutions and seeks out energy-guzzling zombie servers—be they physical, virtual or cloud entities. Data centers can finally reap the benefits of a comprehensive infrastructure management platform that far exceeds ordinary monitoring of power and cooling.
RAMP DCIM monitors and manages all layers of on-premises infrastructure: facilities (CRAC, UPS, PDUs), IT (servers, storage, network), and virtual machines (VMs). It even allows users to monitor their public cloud computing instances in AWS and Google Cloud. Data center operators finally have a single-pane-of-glass view of their entire, holistic infrastructure—facility, IT, virtual and public cloud.
“Power management tools found in the latest breed of DCIM software can be invaluable for today’s data centers, ” said Michael L. Ross, a data management consultant who has over 10 years of helping large data centers reduce their total cost of ownership.
Larger data centers have been the focus of energy efficient solutions due to the positive return on the investment. In a large part, this return is realized through identified energy saving projects identified through the use of DCIM software. On a percentage basis, the energy savings were thought to be the same for smaller data centers but the cost of implementing DCIM software was consider too high to realize those savings. The latest breed of DCIM software, like Tuangru’s RAMP, and its auto-discovery capability, greatly reduces the implementation cost allowing smaller data centers to have a positive return on investment.
About Jad Jebara
Jad Jebara is president and CEO of Tuangru, a next-generation data center infrastructure management (DCIM) software provider. He previously served as senior vice president of finance and administration at Peer 1 Hosting (now Cogeco Peer 1), a hosting service provider where he was responsible for finance, supply chain, and IT.
About Rajan Sodhi
Rajan Sodhi is CMO of Vancouver, Canada-based Tuangru, a next-generation data center infrastructure management (DCIM) software provider with tools that are as meaningful to the C-suite as they are to operators. Users get actionable intelligence that allows them to reduce IT cost, manage workloads and mitigate outages. Contact Mr. Sodhi at email@example.com.
Tuangru’s next generation data center infrastructure management (DCIM) software is designed for today’s hybrid IT environments. Whether workloads reside on-prem, in edge data centers or in the cloud, Tuangru’s DCIM provides managers with a holistic view of their entire infrastructure for management and optimization. The company was recently recognized as one of the fastest growing companies in North America by Deloitte Technology Fast 500™. Tuangru is also a contributor member of The Green Grid. For more information, please visit www.tuangru.com.