Archive for July, 2013

Asia – the Wild, Wild West of Opportunity

Thursday, July 11th, 2013

As I led Global Data Center Strategy and Development for Yahoo!—a position that I immensely enjoyed and would love to do again—I developed, sought out and negotiated data center capacity in over 20 counties. And of all the regions, Asia was by far the most challenging to find large blocks of good quality data center capacity. I spent much time looking for data center capacity to lease in Hong Kong, Taiwan, Singapore, Japan, Korea, and India. (China was a separate entity.) I have taken countless trips to Asia since 2004, and during my tenure at Yahoo!, I traveled to Asia every month (as well as elsewhere).

Due to this limited supply of high-quality data center capacity, I was willing to take down futures on good quality data centers to be built in Asia, especially those with network neutral connectivity, which can be difficult to find in many Asian countries due to limited access to cross-country networks except by incumbent network providers. My counterparts at Google and I were almost always rushing to get into the available data centers in these regions before each other, so I was always so surprised that the US data center providers were not rushing to build strategic capacity in Asia to take advantage of these business opportunities.

Although data center capacity in Asia has been continually added faster than probably any other global region, demand still persists for good-quality, network-neutral data centers throughout Asia. This is evidenced by correlation to network growth mentioned in this statement about Equinix expanding in Osaka: “Osaka is Japan’s second largest economy after Tokyo and saw internet traffic grow a staggering 68 percent and bandwidth increase at a compound annual growth rate (CAGR) of 56 percent from 2008 to 2012 rivaling Tokyo.”

In large, mature and well-developed markets such as Osaka, intrinsic organic market demand doesn’t grow by 56% CAGR, so this indicates to me that there is likely unmeant demand finally being absorbed by new capacity. I believe that the same is true for other recent data center expansions in Asia by Equinix, Digital Realty Trust, and others.

Other locations, particularly Brazil and Mexico, have also been seeing tremendous growth that has been fairly unmeant by high-quality US data center providers. This has also been a challenge for other global locations. So even though US and non-US data center providers have been adding capacity and finally expanding into new global markets, it isn’t enough to have met and continue to meet new demand in these non-US markets.

It’s well beyond time for US data center providers to change their US-centric focus on US locations and take advantages of the many opportunities outside of the US, which can not only provide excellent revenue and margin growth, but also benefits of customer retention and new customer acquisitions, as well as network interconnectivity and market share dominance. All of these being immensely valuable in a much more competitive and global marketplace than it was even just a year ago. It’s time to smartly expand globally to gain many great advantages and cease the ultra-conservative approach that misses market share, revenue and margin growth opportunities for high-quality data center providers.

I hope that I can help guide some of these providers with these new opportunities and also the end-users find the best providers in these growing data center locations. Growth opportunities are nearly boundless in this global market. Now get out there and grow!

Apple+Reno+Solar = “Controllable Power”

Monday, July 8th, 2013

Some of you know that I have developed the Reno Technology Park along with a few others. I am the sole data center expert in the group and when I first viewed the property, I saw that it had potential as a site for data centers with the property being laced with electricity and natural gas transmission lines, main fiber routes crossing thru the property, and proximity to clean power plants. However, that infrastructure was not enough to sway me to get involved. The project needed lower cost power and tax options.

At my insistence, we created some unique tax incentives, but as a data center power guy for nearly two decades negotiating power deals and developing power plants, I saw the real potential was for clean, “controllable” power. I brought Apple to the site last spring and they too saw the same potential.

Fast forward now just over a year, and Apple has one operational data center building, a second data center building fast approaching commissioning, and now an announcement of a nearby 18-MegaWatt solar project near the Reno Technology Park. Here are some links to public articles about these announcements:

Being under NDA with Apple, I cannot expand upon these articles with information from other sources. So let’s talk about what I mean by “controllable power”. The ability to take control of what I call the “Three C’s”: cost, capacity and control. Control being the deliverability, schedule and mix of that power, as well as controlling the future cost of the electricity. Cost being current and future costs, as when we plan to operate a data center, we must take into account the total electricity cost over the expected life, usually 10-20 years. And ideally, we don’t just want a low cost today, but more importantly a low average cost over that life cycle. I see too many folks run to a market with low-cost electricity today but not realize that those low costs will go up, and often within 1-3 years and to an average much higher than other location options. Predicting and seeing these future costs is one of the key advantages to using MegaWatt Consulting for your data center site selections and not another company, as I do not see any other company looking at all of the factors that will influence future data center costs like we do. Do you want to choose a site that has great costs before you start constructing yet high costs by the time you fill it and be surprised that your site is not a low cost site a few years from now, or go to a site that will continue to provide low costs for years to come?
And capacity is key, as there is a cost to bringing power capacity to a project and sometimes that is enormous. For example, a few years ago I was consulting for Equinix and the cost they were quoted by the utility to bring power capacity to a site was equal to nearly one-third of the construction cost for an entire new and large data center! That would have added nearly 50% to the total construction budget! I was able to negotiate that down to less than 10% of the total project budget, but still a very large expense and one that is often not accounted for during site selection TCO estimates. All proving the point that controllability of power over time–each it’s cost, capacity, mix and deliverability—provide significant benefits to a company and it’s costs over time.

Whether or not Apple is responding to pressure from Greenpeace, NY Times’ articles, their stockholders, consumers or other shareholders, having a data center site that can provide flexibility for the many factors over time is key to adjust to changing needs. Whether those needs are costs, the fuel mix, deliverability or reliability of that power, all provide significant benefits when they can be controlled to meet changing needs over time. And all needs change over time, and being that electricity cost drives a 10-year Net-Present Value analysis of data center ownership, “controllable power” is essential to good data center cost management.

If you’d like “to take control” of your data center’s a key driver of current and future costs, as well as combat changing pressures from shareholders, markets and other factors, let’s talk about some options.