Key Take-Aways of Colocation Research for Silicon Valley Power

Last fall EMI, under subcontract to Summit Blue Consulting (now a part of Navigant Consulting), performed a process evaluation for Silicon Valley Power (SVP) in Santa Clara California.  The process evaluation focused on identifying barriers to colocation data centers (or “colos”) participating in SVP’s energy efficiency programs.  Colos provide data center infrastructure to support other companies’ IT equipment – basically data center space for rent.  This space can be leased in units as small as half a rack and as big as thousands of square feet.  The latter situation, where whole rooms or even whole data centers are leased to one tenant, are known as “wholesale” colocation facilities.

Santa Clara has a dense concentration of data centers and colocation facilities.  This is largely due to their location in the heart of Silicon Valley, but also is due to their relatively low cost of power and high reliability of their power delivery. As a result of this high concentration, data centers are a main focus of the SVP energy efficiency programs, and in 2007-2008, roughly 60% of SVP’s energy savings came from data center related projects.

EMI conducted this research by performing: online research and a document review of appropriate reports, and in-depth interviews with colo managers from inside and outside SVP’s service territory and other industry experts.  Here are some of the main take-aways from EMI’s research into participation of colocation facilities in SVP’s programs.

• Aggravated Barriers – Since providing reliable data center space is a colo’s main business, some of the barriers to energy efficiency for typical data centers are aggravated in the colocation facilities’ case.  These include an extreme focus on reliability, with little interest in energy efficiency.  It also creates an extreme case of the split incentive, because the people paying the power bill and the IT purchasers work for completely different companies, so there is little motivation to invest in more efficient equipment.
• Pricing Models of Colos Affect Investment in Efficiency– Different colocation companies have different methods for splitting up charges for power, cooling and space.  While data centers become more constrained by power and cooling (and less constrained by space), some colocation facilities are moving away from space-based charges and more towards charging directly for power and cooling, which helps create more of an incentive for their customers to save energy.
• Difficulty in Reaching the Colocation Facilities’ Customers –SVP, like other utilities, is restricted to only offer incentives to their customers of record.  This is necessary as it allows SVP to be able to recoup the incentive amounts if the measure does not stay in place for the contracted five-year period, and therefore the measure does not deliver the full five years of savings SVP claims for the measure.  As a result, SVP cannot give incentives to the colocation facilities’ customers, as these customers do not pay SVP for their power, but instead the cost of power is bundled with their colo charges.  This is a major barrier for many utilities to getting colocation customers to participate in virtualization incentives, for example.
• Lack of Expertise for Completing Calculations – Some facilities indicated that they did not have the engineering expertise on staff to complete the necessary calculations to receive incentives, as operating colos are basically “a couple IT guys with a sales department.” SVP offers support to fill out the applications, but some potential participants were not aware of this, so this was an area where better communication of the program offerings could help increase participation from companies that need this support.

All in all, the evaluation found that SVP’s focus on data centers has been very successful and that they are undertaking a lot of efforts to help overcome these barriers such as: emphasizing new construction where the barriers and inertia to energy efficiency are not as great, and offering technical support where it is needed.  Other opportunities lie in collaborating with other utilities to identify new opportunities (e.g., for prescriptive measures which simplify the application process), and investigating new ways to get to colo customers.  Although there are many barriers in place for colocation facilities, this is a large data center market, it is growing rapidly, and it is worth having progressive utilities like SVP continue to push to develop programs and processes to overcome these barriers.

The full report (available here) offers more detail on the colocation market and barriers to their participation in energy efficiency programs.

ENERGY STAR for UPS

Speaking of ENERGY STAR, the EPA released a framework document for the newly announced Uninterruptable Power Supplies (UPS) specification last week.  UPS, like computer power supplies before them, lack industry standard measurement procedures to specify their efficiency.  As the market for energy efficient data center equipment grows UPS makers seem to be increasingly marketing the efficiency of their devices, but manufacturers usually specify 100% load – a condition that a UPS will never actually operate in because many UPS are critically underloaded.  Also similar to server power supplies, many UPS are operated in redundant configurations where the load is split between two UPS in the case that one fails.  This means that a UPS in this configuration could only hit 50% load, max.  The efficiency of power conversion equipment tends to fall off below 50% load, so it’s important to measure and specify the efficiency of loads below 50%, because this is where a lot of this equipment is actually running.

To illustrate the point, here’s a chart of power supply efficiency curves from when I was working on the server specification, which I stole from the ENERGY STAR website:

For servers, EPA specified efficiency all the way down to the 10% load condition because available data indicated that that’s where a lot of the redundant power supplies were being operated.  My guess is that ENERGY STAR will be doing a similar thing with UPS, and then the industry will have a way to compare the efficiency of different UPS solutions across much of their operating range. This should be a great help to utilities looking to get verifiable savings through offering incentives or rebates for more efficient UPS.

EPA is also continuing the trend of pushing for standardized reporting requirements (through a power and performance data sheet) and for real-time power and temperature reporting over a standard network.  This is also similar to the V1.0 server specification and what is being proposed for data center storage equipment. EPA is looking to add similar requirements for all data center equipment so that data centers can be operated more efficiently when the managers have better access to data on what’s actually happening in their data center. The power and performance data sheet will also be helpful for proving the specifications of equipment when applying for rebates and incentives.

Interested stakeholders can download the new documents here, and offer comments by April 2, 2010.

Data-Driven Prescriptive Incentives for Data Centers

I’ve spent the last few weeks reviewing information on utility data center energy efficiency programs for a presentation I’m putting together for AFCOM Data Center World, and have been struck by how few prescriptive programs (or “deemed measures”) are available for data center equipment. The few programs that do exist seem to vary widely and are distributed among different utilities around the country.

The most important information you need for creating these programs are data on which to base your assumptions and calculations, including, data on the typical products in the market (or the baseline) and data on the more efficient offerings.  The delta between these two establishes the energy savings on which to base an incentive.  This was similar in my previous work developing specifications for the ENERGY STAR program for the EPA – the biggest problem was access to quality data of sufficient quantity to really understand the energy use of the products. This is a great strength of the ENERGY STAR program, because as a trusted third party they are able to pull in data from a number of different current, and sometimes future, products to get a real sense of how energy is used across different manufacturers.  When they are pulled together these EPA data sets often seem to be some of the best publically available data sets on the energy consumption of these products – a resource that is useful for the program, as well as for other advocates outside the program.

It seems that the utility industry lacks a similar mechanism to collect sufficient data to develop these prescriptive incentive programs for data center equipment.  The primary source of data seems to be data collected through demonstrations and custom incentive applications.  But the utility industry needs a large amount of data to maintain confidence that the prescriptive programs will deliver actual energy savings that they can reliably claim for their programs. However, the utility industry, like ENERGY STAR itself, has only recently taken the plunge into the data center industry.  A lot of programs have a random assortment of incentives they’ve given out for data centers – an efficient UPS here, an economizer there, a few virtual servers in the mix – and do not seem to be reaching the critical mass needed to gather the quantity of information needed to effectively develop prescriptive programs.

I think this turns into a chicken and egg problem. Utilities sometimes find it hard to get traction on their data center programs because they do not have the prescriptive programs that make it easy for the customer to participate, but without the data from participation in the programs they do not have the information needed to develop the prescriptive programs.  As usual, available data seems to be a bottleneck.  What is needed are some central depositories of data with mechanisms to develop intelligent incentives based on that data.  A lot of different groups and organizations have the potential to work toward this goal (and I believe are doing so), and it is an important goal as more prescriptive incentives would certainly help capture some of the energy savings potential which we all know exists in this industry. I’d be really interested to hear about any potential efforts in this area, so if anyone knows about anything fill me in!