Project Spotlight: Continuous Modeling in Operations – Scoring Data Center Performance with ACE

October 01, 2014   2:30 PM – 3:30 PM Room: 207C 
CEU: 0.1 Audience: Advanced–2032 


Business requirements are changing continuously which drives change in the data center. The data center is meant to be a flexible, blank slate upon which IT services are quickly built, dismantled and reconfigured continuously to enable business agility. But how agile is your data center? Can you quantify the cost and risk of changing the data center roadmap to accommodate business needs?

Are you able to factor into business decisions the risks from change? This spotlight will explore how a global financial institution and a global distribution company used a predictive approach in their operations to increase efficiency, resilience and to maximize useable data center capacity in their facility. By building and calibrating a Virtual Facility for their data center, they were able to undertake a project that resulted in significant energy savings and an increase in usable capacity.

These case studies illustrate how data center operations were able to meet business objectives through continuous modeling, and highlight a new data center performance/risk score called “ACE” (Availability, Capacity and Efficiency).

Learning Objectives:
1) Quantify the risk and cost of change in the data center
2) Consolidate tracking of three interrelated performance metrics that together capture the very purpose of the data center
3) Learn how ACE calculations are made practical by computer modeling of the physical data center
4) Address limitations of popular best practices and why these alone cannot address the underlying causes of availability and capacity utilization problems

Presented by:

Sherman Ikemoto
Future Facilities Inc.

Screenshot 2014-08-12 12.25.30

Posted in Data Center DCIM Datacenter Datacenters Datacentre | Tagged , , , , , , , , , , , , , , | Leave a comment

Predictive Modeling and Simulation for the DataCenter Lifecycle

Watch on September 17th 9am PST – 12pm EST:

Screenshot 2014-08-19 09.29.32

Speaker: Sherman Ikemoto, Director, Future Facilities

Data centers are a key component of modern companies. Senior management in these enterprises assume that future IT related changes demanded by the business can be accommodated within their data center infrastructures.

Alas, this demand for operational flexibility introduces risks (and costs) into the data center itself and hence to the business as a whole. Unfortunately, most companies don’t systematically assess such risks inside their data centers, nor can best practices and rules of thumb adequately address them.

This presentation is about computer modeling – simulation of the data center to analyze and quantify the risks of operational flexibility within data centers, with the goal of moving IT operations from being a cost center to becoming a cost-reducing profit center. The approach will be illustrated with a two year case study from a global financial institution.

Watch on September 17th 9am PST – 12pm EST:

Screenshot 2014-07-23 11.18.15

Posted in Data Center DCIM Datacenter Datacenters Datacentre | Tagged , , , , , , , , , , , , , , , , , , , , , , , | Leave a comment

Empowering the DataCenter Operator – ACE Performance Assessment

Download Here:

Executive Summary by Dave King and Steve Davies

In this third and final white paper in our ACE series, we demonstrate to the data center operator how they can use the Virtual Facility to make the decisions that affect them:can a planned change be made without adversely affecting uptime or resilience? If it does affect it, to what degree does it do so? Recalling our own experiences advising data center operators over the last decade, this paper will show you how predictive modeling using the VF will empower you to make decisions with confidence.


At a high level, the data center is a trade-off between three intertwined variables: availability of IT, physical capacity and cooling efficiency (ACE).

In our previous papers, Five Reasons your Data Center’s Availability, Capacity and Efficiency are being Compromised, and From Compromised to Optimized: An ACE Performance Assessment Case Study, we established that mismanaging these variables causes costs to escalate. We also proposed a method, predictive modeling, of sustainably managing ACE in order to reach the goals of the business.

This focus on the operational flexibility and high-level goals of the business is all very nice for the most senior levels of an organization, but what does it mean for you, the operations team? After all, you’re the people who are the ‘boots on the ground’; the people tasked with the actual day-to-day running of the data center.

You will no doubt have first-hand experience of tools and methodologies that have been prescribed from above in the mistaken belief that they will improve efficiency, or prevent downtime, or help you manage capacity. In our experience, the majority of these actually make your job harder to do, so they eventually get left by the wayside.

Making Your Life Easier

So, how is our proposal any different? What we hope to show you in this paper is that predictively modeling using the 6SigmaDC suite’s Virtual Facility (VF) will not only fit into your day-to-day process seamlessly, but also make your job easier and your life less stressful.

How many times have you approved a change that fit within the design rules, only to receive a call telling you that IT service has been interrupted and that you have to fix it, right now? Probably enough for you to think that it is just part of the job; it’s something that comes with the territory, right? It does not have to be. It is simply a knock-on effect of the fact that instead of managing data center availability, capacity and efficiency as three interconnected variables, your organization is treating them as three separate silos. In fact, they probably haven’t been looked at together since the original design was created at the start of the facility’s life.

Given the fast pace of change within any organization, the chances are fairly small that the IT plans put together by the design consultant bear any resemblance to the equipment that is actually installed in your facility today – there is a colossal disparity between the design and the reality. Add to this IT disparity the various energy efficiency drives which will have changed the infrastructure from the original design, and you are left trying to fit square pegs into round holes.

Adding more environmental monitoring will have helped choose which holes to avoid and will have reduced the number of critical events, but firefighting is still a large part of your job. A large number of those fires could be avoided if only you were provided with the right information. This is precisely what predictive modeling does.

What we intend to show in this paper, through the use of examples based on
our decades’ worth of experience in the data center industry, is how predictive modeling is an essential tool in your fight against downtime. We will demonstrate how the data from a VF can provide you with crucial information that is simply not available using any other method. Finally, we will show you how our new ACE Data Center Performance Score provides a simple way to analyze, compare and communicate the effect different options have on a very complex system.

Download Here:

Posted in Data Center DCIM Datacenter Datacenters Datacentre | Tagged , , , , , , , , , , , , , , , | Leave a comment

The Calibrated Data Center


It seems like a day doesn’t go by where I don’t read something about Software Defined Data Centers (SDDC). While nobody seems to have settled on an actual definition of what a true SDDC is supposed to do, the overall concept seems to have everybody excited. While I don’t dispute that SDDC seem to be a logical path for the industry to take, I don’t see many articles quoting any real sales figures which leads me to believe that many data center operators are taking a “you go first” approach to adoption. This makes sense, since solutions advertised as “all encompassing”, tend to be somewhat confusing when a potential customer just wants to know which server is running the company’s email. While we are all waiting for the Rosetta Stone of SDDC, there are software applications available today that can provide real value in the areas of data center calibration and capacity planning.


Calibrating your data center is a proactive process that enables data center operators to fine tune their facilities and identify potential operational issues at the component level. A service provider, for example, could use this process to maximize the sellable capacity of their facility or to provide actionable criteria within the customer SLAs. This process requires both CFD and component level modeling tools. In recent years multiple vendors have arisen to provide this functionality. Here at Compass we use Future Facilities’ 6SigmaDC product for the CFD modeling component and Romonet’s system modeling tool for the TCO component and system level analytics.

Calibrating a data center is required due to the fact that no two data centers operate exactly alike (except, of course, in our case). The calibration process provides data center operators with the specific benchmarks for their facility that can then be used to determine the impact of operational actions like the moving or adding equipment on the raised floor will have on overall site performance. The calibration process begins during the design process for the facility by evaluating the performance on multiple floor layout scenarios. The adoption of the final layout model then provides the initial benchmark standards that will be used in calibrating the facility. The calibration effort consists of comparing these initial benchmarks to the site’s actual performance during a series of progressive load tests conducted upon the completion of the facility’s Level 5 commissioning.

The completion of the site’s commissioning efforts is important since it eliminates an assortment of extraneous variables that could affect the final values reported during the load testing. During load testing the site’s performance in a number of areas including cooling path considerations like the airflow from AHU fans to floor grills or from the grills to cabinets is documented and compared to the initial modeled values to determine if there are any variances and whether those deviations are acceptable or require corrective action. The conclusion of this process results in the establishment of the performance metrics that apply to that data center specifically.

Certainly the establishment of performance benchmarks for the data center is a valuable exercise from a knowledge perspective, but the real value of the calibration effort is resulting ability for operators to continuously model the impact of future site modifications on its performance. The continuous modeling capability manifests itself in more effective capacity planning. The ability to proactively analyze the impact of site modifications like cabinet layouts, increasing power density or hot aisle/cold aisle configurations enables important questions to be answered (and costs avoided) by determining the most effective mode for their implementation prior to the initiation of the first physical action.

Aside from the practical value of the ability to use currently available software tools to perform calibration and continuous modeling activities, they can also provide operators with the ability to prepare for a software-defined future. Developing an on-going understanding of operationally effecting actions provides a foundation of knowledge that can pave the way for the more effective implementation of a “comprehensive software solution” in the future.

Posted in Data Center DCIM Datacenter Datacenters Datacentre | Tagged , , , , , , , , , , , , , , , , , , , | Leave a comment

How Predictive Modeling can work with DCIM to reduce risk in the Datacenter


by Dave King

The human race has acquired an insatiable demand for IT services (or rather the 35% that have access to the internet has), services that have to be available 24 hours a day, seven days a week.

As this demand has grown, data centers have evolved to become either the place where all revenue is generated, or the place that enables all revenue generation for a business.  Just as I am writing this, an advert has popped up on LinkedIn for a Network Infrastucture Engineer for Greggs the Baker (for our international readers, Greggs are a high street baker; they sell cakes, pasties and various other tasty things). That’s right, the baker needs to employ someone well versed in Linux, Cisco and Juniper!

Back in the old days, operators could fly by the seat of their pants, using gut instincts and experience to keep things running.  A little bit of downtime here and there wasn’t the catastrophic, career-ending event it is today. But, as the data center has undergone its transformation into the beating heart of the digital business, the pressure on those poor souls looking after the data center environment to keep it up 24/7 has gone through the roof.

In response to this, managers have invested heavily in monitoring systems to understand just what the heck is going on inside these rooms.  Now armed with a vast amount of data about their data center (interesting question: how many data centers’ worth of data does data center monitoring generate?), and some way to digest it, people are starting to breathe a little easier.

But there’s still a nervous air  hanging over many operations rooms. Like the bomb disposal expert who is fairly sure it’s the green wire, but who is still going to need a new pair of underwear, people are left watching those monitor traces after any change in the data center, hoping they don’t go north.


Meet Bob. Bob works in data center operations for MegaEnterpriseCorp Ltd. It’s his job is to approve server MACs (moves, adds, changes), and he is judged on two criteria:

  1. No increase in the PUE value for the facility
  2. No loss of availability under any conditions, barring complete power failure.

The boss also dictates that unless Bob can prove that a MAC will fail either criteria, as long as there is capacity in the facility, it must be approved.

If a MAC fails on 1 or 2, or if Bob says no to his boss, he risks a new pink slip.  Bob has at his disposal the most comprehensive DCIM monitoring solution you can imagine.  What would you do in this situation?

Let’s think about this for a minute. Say that the equipment to be installed had a fan more like a jet engine than a server; Bob has a gut feeling that it’s going to cause all sorts of problems. How could he prove that it would fail either criterion? Thanks to his all-singing-all-dancing DCIM stack, he has all the information he could want about the environment inside the data center right now. It’s saying that that all looks fine, mostly because the horrible jet server hasn’t been installed yet.

The only way to find out what kind of carnage that server may wreak on the environment is to install it, switch it on and watch the monitor traces in trepidation to see what happens.  If the PUE doesn’t change then great, but how much headroom have you lost in terms of resilience? The only way to find out? Fail the cooling units and see what happens…


The more astute among you will have noticed that this is a lose-lose situation for poor old Bob.  He can’t stop any deployments unless he can prove they will reduce availability or have an impact on PUE, but he can’t prove they will cause problems without making the change and see what happens! Catch-22!

The problem is that all the changes are being made to the production environment; there is no testing ground data center to make mistakes in – it’s all happening live!  And that’s why everyone is on the edge of their seat, all the time.  In many other industries, simulation is used in situations like this – where physical testing is impossible or impractical – to allow people to see and analyze designs changes and what-if scenarios.  There is no reason the data center industry should be different.


Let’s go back to Bob, but this time we’ll give him a simulation tool in addition to his DCIM suite. For each proposed MAC, he sets up a model in the simulation tool using the data from the DCIM system and then looks at the simulated PUE and availability. He can fail cooling units in the simulation without any risk to either the IT or himself.  If PUE goes up, or availability goes down, Bob can print out the simulation results as proof, say no to his boss and keep his job.

As a senior consultant engineer who has been parachuted into troubled data centers the world over, and who has had the opportunity to advise lots of Bobs over the years, it still amazes me that the uptake of the obvious solution is not more widely spread. The case for simulation is compelling, so why has the adoption of simulation in the data centre industry been so slow? A lack of awareness is certainly a factor, but it has been seen by many as unnecessary, too complicated and inaccurate.  Let’s address these points…

While the benefits of simulation have always been there to be had, it is certainly true that in the past there was an argument for placing it on the “nice to have” pile. Thermal densities were much lower and over-engineering more acceptable. But, as data centre operations have been forced by business to become leaner, the operational envelope is being squeezed as tightly as possible. The margin for error is all but disappearing, and having the ability to test a variety of scenarios without risking the production environment places organizations at a big advantage.

Simulation tools can be complicated and it would be wrong to say otherwise. But this complexity was an unfortunate consequence of the deliberate intention to make these tools versatile. Here at Future Facilities, we’ve spent 10 years doing the exact opposite: making a simulation tool that is focused on a single application: data centers. This tool is aimed at busy data centre professionals, not PhD students who have hours to spend fiddling with a million different settings.  This means that modelling a data center is now as simple as dragging and dropping cooling units, racks and servers from a library of these ready-to-use items. Take a free trial and have a go yourself!

That just leaves us with the question of accuracy.  The accuracy of CFD technology has already been proven – the real problem comes down to the quality of the models themselves. Make a rubbish model and you’ll get meaningless results.  Many in the data centre industry have been burned in the past by simulation used badly, but this is a ‘people problem’ – operator error – not an issue with the technology!  If you’re going to use simulation, the model has to represent the reality and must be proven to do so before it’s used to make operational changes. This process of calibrating the model ensures that agreement between simulation results and physical measurements is reached (read this paper to find out how the calibration process works).  If someone is selling you simulation and isn’t willing to put their money where their mouth is, be very, very wary.

There’s just room here for me to say a few words on “real-time CFD” or ‘CFD-like’ capabilities – the latest strap-lines for a number of DCIM providers. We’ll blog about this separately in the future, but let us be very clear: there is, at present, no such thing for data centers. It is marketing hype.  When people talk about real-time CFD they can really mean one of two things: 1) they can either use monitor data to make a picture that looks like the output of a simulation, with zero predictive capability, or 2) they use a type of CFD known as potential flow which trades accuracy for speed by making a lot of assumptions.  Renowned physicist, bongo player and all round good guy Richard Feynmann considered potential flow to be so unphysical that the only fluid to obey the assumptions was “dry water“.

So the questions you have to ask yourself is do I want a tool that can actually predict, and do I want a tool that can predict accurately. A full CFD simulation (typically RANS) may not be real-time, but it is the only way to get the real answer!




Posted in Data Center DCIM Datacenter Datacenters Datacentre | Tagged , , , , , , , , , , , , , , , , , , , , | Leave a comment




Published on 18th June 2014 by Penny Jones



The divide between facilities and IT teams within the data center created some lively debate this week at DatacenterDynamics Converged Santa Clara. This time the conversation was around unused capacity, cost and risk. Judging by the thoughts of those working here on the US West Coast, the overall responsibility for managing these areas is a real ‘hot potato’ that is turning efforts to drive efficiency and reduce costs to mash.

But it appears to be the fault of no single team or technology. What it really boils down to (not intending to put another potato pun out there!) is a lack of education, or even an ensuing candidate position to assume such a role. It seems IT teams have enough on their plate to start learning facilities, and facilities the same regarding IT. And finance, well they often have other parts of the business to think about, despite paying the power bill. But when things go wrong, this hot potato can cause havoc for all teams involved.

On the evening leading to the event, a roundtable organized by predictive modeling vendor Future Facilities, hosted by industry advisor Bruce Taylor and attended by a number of industry stalwarts and a handful of newer industry members, discussed hindrances to capacity planning. Most agreed that the main reason we have stranded capacity in the data center is that the industry has created so many silos – teams working on individual projects inside the facility – that there is rarely someone tasked with taking on the bigger picture, looking at the farm from the top of the mountain.


Air flow is complicated, and Future Facilities argues that predictive modeling is the only science that can really help when deploying, then maintaining levels of efficiency as data center demands – and equipment – change.


Dr. Jon Koomey, research fellow at the Steyer-Taylor Center for Energy Policy and Finance at Stanford University said only when you know the physics of the situation inside the data center, and the effect of changes you are likely to make in future, can you remove the problem of stranded capacity, and in turn drive better levels of efficiency through reduced power use.

“The goal, ultimately, is to match energy services demanded with those supplied to deliver information services at the total lowest cost. The only way to do that is to manage stranded capacity that comes from IT deployments that do not match the original design of the facility,” Koomey said.

He likened the situation today to Tetris, drawing on the analogy of the different shaped blocks in the game.

“IT loads come in to the facility in all different shapes, leaving spaces. Those spaces are capacity, so that 5MW IT facility you think you have bought will typically have 30% to 40% unused.”

Despite the obvious draw for making maximum use of your data center many attendees agreed that predictive modeling, and even data center infrastructure management (DCIM) tools that offer more clarity on the individual situation at real time, can be a difficult sell. Once again, the hot potato (of no one tasked with complete responsibility) often gets in the way.


Mark Thiele, EVP of data center technology at Switch, who has also worked for ServiceMesh, VMware and Brocade, said in most cases there is not a single person in the data center with a vision or understanding of the facility’s entire operations – from design and build to IT, facilities and even economics.

“Today 75 to 80% of all data centers don’t have a holistic person that knows and understands everything about the data center, so the target opportunity for [sale of] these tools is often someone that has no responsibility for managing this in their job description,” Thiele said.

“We also find that a majority of facilities today are still bespoke – they are designed to be repaired after they are created. These are serious thresholds that have to be overcome in the market on the whole.”

But this is a situation the industry has created for itself, according to dinner host and Future Facilities CEO Hassan Moezzi.

“If you go back to IBM, 40 years ago it dominated the mainframe market. At the time, the concept of IBM having blank cheque for customers was a really painful thing but everyone accepted that because it was the only way. IBM built the power, cooled the data center and provided the hardware and software and if anything went wrong with the data center it was all put back on to IBM,” Moezzi said.

Today we have the silos and distributed systems we have asked for. Anyone can buy a computer and plug it into a wall. The shackles have gone, and so too has that one throat to choke – or to sell capacity planning systems to.

Continue Reading this article here: 

Posted in Data Center DCIM Datacenter Datacenters Datacentre | Tagged , , , , , , , , , , , , , , , , , , , , , , , | Leave a comment

Future Facilities Hosts Executive Dinner with Jonathan Koomey and Bruce Taylor



An Evening with Dr. Jonathan Koomey & Bruce Taylor

FF model data center logo large

On June 16, 2014, in Santa Clara, CA, Future Facilities hosted top executives from IT companies in the Bay Area to join together in conversation facilitated by Dr. Jonathan Koomey of Stanford University and Bruce Taylor of Data Center Dynamics. A unique & intimate evening of networking, dinner, & drinks, this event featured a lively conversation on some controversial views on risk in the data center and its impact on the business. Attending industry experts and analysts discussed ways to use computer modeling to analyze and quantify risks and costs of operational flexibility within data centers, with the goal of moving enterprise IT operations from being a cost center to becoming a cost-reducing profit center.




Posted in Data Center DCIM Datacenter Datacenters Datacentre | Tagged , , , , , , , , , , | Leave a comment