Driven by non-governmental organizations (NGOs) and a more informed general public, which itself has become more and more frequently impacted by climate change first-hand, investors have finally gotten the memo. There’s only one Earth, and I’m sure we can all agree without controversy that no killer app, social media or eCommerce platform, or streaming binge marathon will ever be worth its sacrifice.
For these and other reasons, the need for environmental stewardship applies to data center owners and operators too, of course. And not just the ultra-efficient, hyperscale facilities run by the likes of Apple, Amazon, Facebook, Google and Microsoft who are increasingly making good on their commitments to renewables, but also to enterprise data centers, colocation providers and their customers.
According to research that appeared in the academic journal Science, the world’s data centers consumed 205 terawatt-hours (TWh) of electricity in 2018, or about one percent of all electricity consumed in that year worldwide. The data center industry is presently growing at a rapid pace, which means the industry is only increasing its electricity consumption. Hence, on balance, and despite the increased use of renewable energy sources, data centers remain a significant source of greenhouse gas or carbon emission power consumption for many mid to large-sized organizations.
These matters become further disconcerting when you consider that the authors of the aforementioned study also predicted that data center energy usage in some countries may increase to levels of 15-to-30 percent of their total domestic electricity consumption by 2030.
Over the past tumultuous and data-driven year, we’ve already witnessed skyrocketing demand for streaming and social media, video conferencing and cloud collaboration platforms, and cloud gaming as global populations adjusted to working, playing and learning from home. Meanwhile, AI applications and high performance computing are becoming ever more prevalent across the cloud and enterprise. And what data and energy demands the mainstreaming of, say 5G, the IoT, and autonomous vehicles will bring to bear on our environment are questions for yet more research and studies.
In 2019, Bitcoin alone used approximately seven gigawatts of electricity, equal to 0.21% of the world's supply. While that number might seem modest, this would equate to roughly the same power consumption as Switzerland, according to research by the University of Cambridge. In fact, according to a more recent Cambridge study, if Bitcoin were a country, today it would rank among the top 30 energy users worldwide, just behind Norway (122.20 TWh), but ahead of Argentina (121 TWh) at 121.36 TWh annually.
One welcome certainty is that there are many opportunities to reduce energy consumption in data centers while lowering costs and curtailing carbon emissions.
Sustainability Is Smart Business
To date, the data center industry’s journey towards sustainability has focused on two distinct paths: Tapping power from renewable energy sources such as wind, solar, hydro and biomass rather than fossil fuels, and reducing total power usage. But according to a recent Uptime Institute report, efforts to improve the energy efficiency of the mechanical and electrical infrastructure of the data center are producing only marginal improvements. And as the Austrian management consultant Peter Drucker famously opined, “You can't manage what you can't measure.”
Now more than ever is the time for IT staff and facilities administrators to turn to data center management solutions to gain the requisite clarity into power consumption, significantly reduce energy use, slash mounting energy bills, and mitigate carbon footprint. Software solutions such as Intel® Data Center Manager (Intel® DCM) can enable facilities and IT professionals to intelligently assess data center energy consumption.
These tools provide real-time power and thermal consumption data, giving IT staff the information needed to lower power usage, safely increase rack density and prolong operation during outages, thus improving an organization’s bottom line.
For example, many data center administrators wanting to prevent infrastructure failures will overcool their systems and waste valuable energy because they lack visibility into actual server temperatures and power consumption. To be fair, such preemptive methods are understandable given an IDC survey of Fortune 1000 companies found that the average cost of an infrastructure failure for such firms is $100,000 per hour, and the average total cost of unplanned application downtime is $1.25 to $2.5 billion per year.
Once again, you can't manage what you can't measure. But by aggregating server-inlet temperature data into thermal maps, data center management software solutions allow IT staff to monitor the effectiveness of their cooling solutions and airflow design. Using a data center management solution’s cooling analysis function, IT staff can lower cooling costs by safely raising the temperature of the room, thereby improving power usage effectiveness (PUE) and energy efficiency, while continuously monitoring hardware for temperature issues.
Based on the historical temperature readings of each server, a global cybersecurity company that deployed Intel® DCM was able to raise the temperatures in its server rooms by 3°C, making possible a 25 percent overall savings for the year on cooling. When a data center manager overseeing a high-density computing environment is provided the necessary data to enable raising the overall set-point temperatures of the room, this capability can significantly lower annual cooling costs across the organization’s entire data center footprint.
In addition to historical data and real-time monitoring of the environment, these software solutions also provide predictive analysis of thermal data that can identify temperature issues before they can cause critical incidents. Moreover, monitoring and aggregating real-time power and thermal consumption data helps IT staff to analyze and manage data center capacity compared to actual utilization, so that power and cooling infrastructure is used as efficiently as possible. In so doing, data center management solutions help identify underused servers, which not only saves power but helps to identify opportunities for consolidation and virtualization, further contributing to energy efficiency and a healthier bottom line.
In data, there are opportunities for sustainability, and in sustainability there is smart business. Despite, or perhaps even in light of, the rigors of the past year, the data center occupies an even better place today because we’ve learned so much about the resiliency of our mission-critical infrastructure, our networks, the edge and the cloud. There is still much more to learn, and in the next phase of the data center industry’s journey towards sustainability, as always, data will be our guide.
