So I’d like to pose a couple of questions: what’s the relationship between real-time power data and capacity planning? And how can this relationship potentially save your data center millions of dollars?

Technically, what I’m referring to here is the use of real time (live) power data vs. faceplate or derated estimates as you do power monitoring and management.

Strategically, what I’m referring to is the use of Data Center Infrastructure Management (DCIM) to fill out your racks and optimize capacity planning based on facts, not guesswork, about the power actually being used on your floor.

Gary Bunyan, a Global DCIM Solutions Specialist at iTRACS^®, recommends thinking about it this way – don’t focus on power, focus on capacity planning and cost containment. How to save your company millions by finding new ways to do more with less. How to increase rack densities within your existing footprint so you can expand capacity without having to build new.

Gary says it’s all about accessing and using real-time power readings that help you make vital decisions about your physical infrastructure – decisions based on knowledge (what you know is happening) vs. guestimates (what you think may be happening) …

In Gary’s monthly DCIM “Notes from the Road” column for Data Center Knowledge, he offers a pretty cool scenario:

“Let’s say one of your business clients has a new initiative and they come to you with a request for more capacity – but your hands are tied, you cannot bring additional power into your facility. You must add the capacity within your existing footprint. This means finding racks with available space and power and then filling them with more servers, safely, without putting power or cooling at risk. Because if you over-commission, the whole environment could come down.

Here’s how real-time data can help you meet the challenge:

Confirming maximum number of servers per rack

(1) You establish a threshold of <45% of available power capacity per rack so full redundancy is assured.

(2) FINDING THE RIGHT RACKS: Using live power readings from Intel® Data Center Manager, you determine current power utilization within your existing racks and confirm the remaining power available to you. It turns out you have more racks with ‘stranded’ (available) power than you thought.

(3) CONFIRMING THE RIGHT SERVERS FOR THOSE RACKS: Using hardware profiling, you confirm which server models currently on your floor deliver the best energy efficiency based on live power readings (their actual performance) – these are the models you’ll want to replicate.

(4) You correlate information about both – the racks that you KNOW have available power based on live data, and the servers that you KNOW offer the highest work-per-watt, also based on live data.

(5) What you confirm is this –

you can deploy MANY MORE servers in these racks than you originally thought possible.

While the manufacturer’s faceplate values indicate only 3 servers per rack, and derated values imply you could maybe increase that to 5 – Intel’s real-time data confirms that you can put 8 servers into each rack. Since the servers are drawing less power than you thought, the racks are safe to fill without exceeding the <45% power threshold.

You now have a clear plan of attack.”

Continue reading part two, about deploying your new servers based on live data, not guesswork.

Where’s some of the most advanced computing infrastructure in the world being built right now? A lot of people would say China. The country is building dozens if not hundreds of large data centers to support its exploding online population, now estimated at 500 million and climbing, according to PCWorld.com.

Reports PCWorld, “The build-out is strongly backed by the Chinese government, which has made expanding the national computing infrastructure a part of its latest five-year plan. And local governments are funding the development of vast cloud cities – industrial zones that aim to provide the foundations to support as many as 20 data centers over time.”

Of course there are a number of major challenges in a build-out this massive, especially for outside companies seeking to participate. These include:

• Governmental policy and regulations, such as ownership rights for data and other assets
• Securing adequate bandwidth
• Securing adequate power
• Carbon footprint

Everything in China is magnified, given the staggering size of the country. “China has almost five times the population of the U.S., so our problems are five times greater,” Sheldon He, a product marketing manager with Intel, reminded PCWorld. But he added, “If we can succeed in solving these problems it could lead to innovation.”

Not just innovation, but big-time innovation.

Global spending on data center hardware is projected to reach $98.9 billion in 2011, an increase of 12.7% from 2010 spending levels, according to a research report from Gartner. As reported in ciol.com, Gartner is predicting that hardware spending in data centers will climb to $106.4 billion in 2012 and surpass $126.2 billion in 2015. Data center IT hardware typically includes servers, storage and networking equipment. Gartner’s research is summarized in its latest data center report, Forecast: Data Centers, Worldwide, 2010-2015.

According to Gartner, the trend towards consolidation – a reduction in the number of midsize data centers while the mega-data centers enjoy robust growth – will continue unabated. By 2015, 2% of all data centers will contain 60% of all data center floor space and account for 71% of all data center hardware spending.

“Traditional in-house enterprise data centers are under attack from three sides,” said Jon Hardcastle, Research Director, Gartner. “Firstly, virtualization technologies are helping companies to utilize their infrastructure more effectively, inhibiting overall system growth. Secondly, data centers are getting more efficient, leading to higher system deployment densities and inhibiting demand for floor space. Thirdly, the move to consolidated third-party data centers is reducing the overall number of midsize data centers.”

“Meanwhile, the largest data center class is, of course, benefiting from the rise of cloud computing,” he added.

Is bigger better? It can be when you deploy enterprise-class Data Center Infrastructure Management (DCIM) to drive efficiency, lower costs, and optimize operational agility. This kind of DCIM is going to be in demand moving forward, as it is specifically engineered to handle large, complex infrastructure environments.