Cookie policy: This site uses cookies (small files stored on your computer) to simplify and improve your experience of this website. Cookies are small text files stored on the device you are using to access this website. For more information on how we use and manage cookies please take a look at our privacy and cookie policies. Some parts of the site may not work properly if you choose not to accept cookies.


Akamai's data center carbon fight

  • Print
  • Share
  • Comment
  • Save

As operator of one of the world’s largest and most important content delivery networks, Akamai has become one of the poster children for the age of the Cloud and for what may be wrong with it. Greenpeace included it on the list of high-profile tech companies representative of the Cloud’s environmental impact, thereby thrusting the company into the limelight of public scrutiny of the issue.


The CDN provider was one of only two companies to receive an ‘A’ on the environmentalist organization’s 2012 report card that scores companies on the lengths they go to in reducing their impact on the environment. The other company with an ‘A’ was Google.


Akamai is also the only company on the report card that could not provide information about the fuel mix used by utilities that supply energy for its infrastructure, since it does not own its data centers. In July, we caught up with Nicola Peill-Moelter, Akamai’s director of environmental sustainability, at the DatacenterDynamics Converged conference in San Francisco to talk about the issues facing a company under public pressure to reduce its carbon footprint.


Own data centers considered

While Peill-Moelter did not want to disclose the exact number, she did say that Akamai’s network lives in more than 1,000 data center locations around the world. The company owns and operates all of its servers but hosts them exclusively in colocation facilities operated by outside providers. This strategy will likely adjust in the near future to include some owned and operated facilities.


“In certain locations, we have very large deployments of servers, and, because of the evolving modular data center technology, it seems that … it would be in some cases more cost effective for us to own and operate our own data centers,” she explains. “We believe the cost effectiveness comes through energy efficiency, which would then reduce the carbon footprint per unit of traffic on the network.”


Akamai gives ‘F’ for efficiency to most colos

In Peill-Moelter’s world, a transition of a substantial portion of the network to an in-house data center would make a huge difference. Most data center providers hosting Akamai’s severs in their facilities have not done much to improve energy efficiency, she says, attributing this to a lack of market incentives to get more efficient and poor data collection on behalf of data center operators.


“We see that in the data center providers that we’re with,” she says. “The vast majority of them really aren’t doing a whole lot around energy efficiency, which ... is very surprising.”


She is surprised with the slow rate of adoption of new energy efficient data center infrastructure designs and technologies because of the volume of information on efficiency and its positive effect on the data center operator’s bottom line that is out there.


She says this is probably because operators do not compete on efficiency. An operator usually passes the cost of inefficiency to their tenant, and, as long as their competition continues doing the same, they do not see that there is a whole lot of business advantage to be gained from investing in efficiency improvements.


Calculating carbon

Another reason for inefficient colos, from Peill-Moelter's observations, is lack of proper efficiency measurement practices. Efficiency metrics (specifically PUE, or Power Usage Effectiveness) are important to her personally, because Akamai uses PUE to determine its data center network’s total power consumption and calculate the volume of carbon emissions its operation is responsible for every year.


Without PUE, the company has only half of the information it needs to determine how much power it consumes. That half is the power consumption of its servers.


Before an Akamai server is installed in a data center, its maximum power draw is measured in a lab, Peill-Moelter explains. In calculating the infrastructure’s total power draw, it is assumed that the server will draw about 85% of the maximum in production.


The team uses PUE to determine the amount of power consumed by data center infrastructure in the overall calculation. They ask for PUE numbers from about 75% of all data center operators hosting the Akamai network and get a response from about 90% of them.


“The question would be how accurate those PUE numbers are,” Peill-Moelter says. “We really have no mechanism at this point to assess the accuracy of the PUE numbers.”


When a provider cannot produce a PUE number or there are reasons to believe the numbers they provide may be inaccurate, Akamai plugs an industry average – which she says is about 1.9 – in its formula.


Moving targets

This data is a crucial driver of Akamai’s operational decisions, since it comes up with yearly carbon-reduction goals. The goal for 2012, for example, was to reduce carbon intensity by 30%.


For Akamai, carbon intensity is the number of metric tons of carbon-equivalent gasses emitted per gigabit of traffic transmitted per second. While the company did not reach its carbon-intensity reduction last year – it was reduced by 25% – the total amount of carbon emitted as result of its operations went down by more than 30%.


This happened because the company achieved a higher carbon-intensity reduction in the beginning of the year than it did toward the year’s end. “Carving out only 25% in carbon intensity, we actually did better in absolute terms,” Peill-Moelter says.


A version of this article first ran in the latest edition of DatacenterDynamics FOCUS magazine.

Related images

  • AkamaiÔÇÖs network operations command center in Boston, Massachusetts

Have your say

Please view our terms and conditions before submitting your comment.

  • Print
  • Share
  • Comment
  • Save


  • Overhead Power Distribution – Best Practice in Modular Design

    Tue, 10 Nov 2015 16:00:00

    Overhead power distribution in your data center offers many attractive possibilities but is not without its challenges. Join UE Corp’s Director of Marketing, Mark Swift, and CPI’s Senior Data Center Consultant, Steve Bornfield, for an exploration of the options and some of the pitfalls, supported by real-life examples from the field.

  • Overcoming the Challenges of High Power Density Deployments

    Wed, 4 Nov 2015 19:00:00

    Increasing rack power densities saves space and energy, and improves both OPEX and CAPEX. But it can also create unintended problems that could bring your data center to a screeching halt. Join Raritan’s VP of Products & Marketing, Henry Hsu, and DCD’s CTO Stephen Worn, as they reveal the three key challenges in deploying a high density cabinet, and explain how to: Reduce operating costs, Increase up-time , Improve mean time to repair, become more energy-efficient manage existing capacity and plan for growth.

  • Squeezing the Lemon - The Power to do More with Less

    Tue, 20 Oct 2015 08:00:00

    Energy costs rising, manpower resources falling – managing a data center is getting more stressful by the day. One cold night could be all it takes to tip your power supply over the edge. And let's not forget the never-ending demands from IT for additional space. More information on its own is not the answer. Join Rittal's webinar to understand how to: • Lower your power consumption and OPEX charges, with 'smart' power distribution • Identify issues before they become problems, with intelligent PDUs' monitoring capabilities • Expand your DC as your business grows, with modular PDUs • Profile your power requirements to help you plan and make better-informed decisions REGISTER NOW Note: All attendees will receive a free copy of the latest White Paper from Rittal.

  • Live Customer Roundtable: Optimizing Capacity (12:00 EST)

    Tue, 8 Sep 2015 16:00:00

    The biggest challenge facing many data centers today? Capacity. How to optimize what you have today. And when you need to expand, how to expand your capacity smarter. Learn from the experts about how Data Center Infrastructure Management (DCIM) and Prefabricated Modular Data Centers are driving best practices in how capacity is managed and optimized: - lower costs - improved efficiencies and performance - better IT services delivered to the business - accurate long-range planning Don;t miss out on our LIVE customer roundtable and your chance to pose questions to expert speakers from Commscope, VIRTUS and University of Montana. These enterprises are putting best practices to work today in the only place that counts – the real world.

  • Power Optimization – Can Your Business Survive an Unplanned Outage? (APAC)

    Wed, 26 Aug 2015 05:00:00

    Most outages are accidental; by adopting an intelligent power chain, you can help mitigate them and reduce your mean-time to repair. Join Anixter and DatacenterDynamics for a webinar on the five best practices and measurement techniques to help you obtain the performance data you need to optimize your power chain. Register today!

More link