The Future is Now: How the Next-Gen Data Center Optimizes Energy Use for Increased Sustainability

Nov. 16, 2022
Joseph Reele, VP Solution Architects for Schneider Electric, explains why the need for more energy will drive operators to “rethink” design, operation, and maintenance of Edge, network edge, micro-edge, and interconnected data centers.
Look around: data is everywhere, and we’re all dependent on it. Accordingly, global data center capacity continues to grow at an exponential rate — a pace that is stressing the electrical grid.  Various estimates for the global energy consumption in data centers range from 1% to 2% of the world’s energy consumption. This figure translates to around 900 terawatt hours annually and approximately .3% of overall carbon or greenhouse gas (GHG) emissions.

This level of data center capacity constitutes the here and now. Think about the near-term growth fueled by the rapid acceleration of digital transformation. Nearly every industry – finance, retail, manufacturing, healthcare, education, government – is fast-adopting digital technology and customer-facing digital experiences to build or pivot, sustain, and grow their business. As we know, digital technology is inextricable from compute, network, and storage — not to mention the internet of things (IoT) and applications that can be used or accessed at any time, from anywhere.  When you add mobile devices to the above data center GHG at .3%, this number grows to almost 2% of the world’s GHG!

If you ask me, this scenario sounds like a data center. The truth is that everything is starting to look and act like a data center.  Some may call this “edge computing”; others may call it distributed networks. Whatever you want to call it, the reality is this: next-gen data centers are no longer just big, windowless buildings with rows upon rows of servers containing countless beeping blue lights. And so, the “digital infrastructure” that is “core” (compute, network, and storage) to all data centers is suddenly in a lot of places and in smaller footprints.  Needless to say, these environments consume energy! And a lot of it. Gartner reports that by 2025, 75% of enterprise data is expected to be created and processed at the edge. Worldwide spending on edge computing is expected to be $176 billion in 2022, an increase of 14.8% over 2021. Enterprise and service provider spending on hardware, software, and services for edge solutions is forecast to sustain this pace of growth through 2025 when spending will reach nearly $274 billion, according to the International Data Corporation Worldwide Edge Spending Guide.

The drive for data center capacity is primarily fueled by two things:

  1. Cloud & Service Providers: Widespread digitalization & cloudification, everywhere

As much as I personally enjoy analog indulgences such as an “old fashioned watch,” we’re never going back to the early digital days of beepers and fax machines. Today’s digitalization requires more compute, network, and storage capacity — all of which translates into the need for more energy. From “hyperscale cloud” and collocation to regional data centers, industry analysts forecast growth between 5% to 10.5% CAGR through 2032.  And this market should continue to see growth and expansion. 

  1. The Edge: The need for more bandwidth and speed!

The “autonomous age” (cars, same-day delivery drones, electrical vehicle (EV)-charging networks, smart grids, cities and buildings, Industry 4.0, manufacturing, etc.) rely on a low-latency, high-bandwidth network infrastructure to support speeds demanded by both mission-critical applications and consumer-driven expectations. And did I mention that widespread 5G adoption is just around the corner, essentially putting current capacity needs on steroids? Simply said, localized compute, network, and storage — combined with a more efficient network that “interconnects” an increasing number of devices and applications — now need the computing brains of their cloud-based cousins. 

Think of it at a super high level: today’s internet – built during the days of Al Gore and AOL (as in “You’ve got mail!”) – was roughly designed to connect people. Now, we need an information superhighway for the “autonomous age” (the metaverse included) — one that connects machines and things, not people. And there are way more machines and things than there are people. The world population is around 8 billion and there were approximately 20 billion connected devices in 2020 with estimates of a 14-16% annual growth rate.

Let’s take a deeper look into the need for more bandwidth and speed. This is a big driver in investments; infrastructure builds from networks (fiber, 5G) to hyperscale to regional data centers; and still many more interconnects. All will require much more energy, in turn driving the need to “rethink” design, operation, and maintenance of Edge, network edge, micro-edge, and interconnected data centers.

Meeting the energy needs of skyrocketing data center capacity

The burning question, then is: “How can we solve the need for more energy while addressing business continuity and uptime?” About 10 years ago, data centers were regarded as “energy hogs,” and we moved the needle on overcoming this characterization. We can’t go back as digital moves forward. 

Typically, to protect business continuity and uptime beyond uninterruptible power supplies (UPS) and battery power with limited run time, diesel generators come into play at most data centers. The shift toward non-fossil fuel-based solutions is not only a sustainability imperative, but also corporate responsibility. Ironically, digital is the key to balancing capacity needs and energy use. It is at the core of the following five ways forward:

  1. An electricity-based “prosumer” model whereby data center owners can both produce and consume electricity using a mix of more green power. Indeed, it is digitalization that enables this two-way street of energy flexibility via smart meters and connected distribution architecture. (Digitalized microgrid is another option for the prosumer model.)  
  2. “Green Hydrogen Production” processes. Traditionally, we have been developing hydrogen production solutions with well-established thermoelectric and electrolytic processes that consume fossil-fueled electricity to split water into hydrogen and oxygen. Green hydrogen production, however, leverages Direct Solar Water Splitting which uses sustainable light energy to split water into hydrogen and oxygen, as well as biological processes which rely on microbes (such as bacteria and microalgae) to produce hydrogen through sunlight or organic matter. In these next-gen green hydrogen cases, there would be no electrical (or fossil fuel) draw from the utility to produce hydrogen.
  3. Adopting battery technology innovations.New chemistry and battery types are leading the way in this area with respect to Battery Energy Storage Systems (BESS) being developed and sized / scaled for utility use.  
  4. Renewable energies such as photovoltaic (PV) and wind power systems, which are also increasing in electrical production / availability. And when these systems are producing more power than the facility needs, power could be put back onto the grid (prosumer).  
  5. Microgrids: A system that can manage several different power sources (such as utility, solar, wind, BESS and even generators) is at the root of this alternative form of maintaining resilience while lowering emissions. The “string” that unites and orchestrates all these renewable sources is Digital Energy Management, Grid, and Microgrid software. This path is the proven formula for electric + digital = sustainable. If orchestrated digitally, sources of electricity can match the demand at any given time for more efficient power production and, by extension, less energy waste.

As this new, next-gen data center landscape takes root, what is rising to the surface? Software-defined solutions. The shift toward more data centers of all sizes, rising energy needs, and increased production requirements is facilitating a shift in the design, operation, and maintenance of many of these remote and/or unstaffed data centers / mission-critical environments. Indeed, gone are the days of hard-wired components screwed into walls.

So, next-gen data centers are the convergence of network systems and software-defined facilities that are tuned for remote management.  As a result, data intelligence and analytics take center stage to make operation, troubleshoot, repair, and maintenance more efficient and flexible. All require more compute, network, and storage. See the loop? Once again, “digitalization” is the driver here, paving the way for more sustainable data centers — both in terms of their green energy use and business growth derived from optimized cost and risk. 

Joseph Reele is VP Solution Architects, Schneider Electric. Learn more by downloading Schneider Electric’s Best Practices to Deploy Sustainable and Resilient Data Centers at Scale at the Network Edge

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

Guide to Environmental Sustainability Metrics for Data Centers

Unlock the power of Environmental, Social, and Governance (ESG) reporting in the data center industry with our comprehensive guide, proposing 28 key metrics across five categories...

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...

iStock, courtesy of AFL

Hyperscale: The AI Tsunami

AFL's Alan Keizer and Keith Sullivan explore how AI is driving change and creating challenges for data centers.

White Papers

DCF_KohlerWPCover_2021-12-08_8-46-39
DCF_KohlerWPCover_2021-12-08_8-46-39
DCF_KohlerWPCover_2021-12-08_8-46-39
DCF_KohlerWPCover_2021-12-08_8-46-39
DCF_KohlerWPCover_2021-12-08_8-46-39

Data Center Generator Maintenance

Dec. 10, 2021
A new white paper from Kohler Power Systems explains the feasibility and benefits of no-load exercising for diesel generator operators.