As an industry, we have been talking about it for some time. Some claimed it would never come and it was just a bunch of fear mongering. Others like me said it was the inevitable outcome of the intensifying focus on energy consumption. Whether you view this to be a good thing or bad thing its something that you and your company are going to have to start planning for very shortly. This is no longer a drill.
CRC – its not just a cycle redundancy check
I have been tracking the energy efficiency work being done in the United Kingdom for quite some time and developments in the Carbon Reduction Commitment (CRC). My recent trip to London afforded me the opportunity to drive significantly harder into the draft and discuss it with a user community (at the Digital Realty Round table event) who will likely be the first impacted by such legislation. For those of you unfamiliar with the initiative let me give a quick overview of the CRC and how it will work.
The main purpose of the CRC is a mandatory carbon reduction and energy efficiency scheme aimed at changing energy use behaviors and further incent the adoption of technology and infrastructure. While not specifically aimed at Data Centers (its aimed at everyone) you can see that by its definition Data Centers will be significantly affected. It was introduced as part of the Climate Change Act 2008.
In effect it is an auction based carbon emissions trading scheme designed to operate under a Cap and Trade mechanism. While its base claim says that it will be revenue neutral to the government (except of course for penalties resulting from non-compliance), it provides a very handy vehicle for future taxation and revenue. This is important, because as data center managers you are now placed in a position where you have primary regulatory reporting responsibilities for your company. No more hiding under the radar, your roles will now be front and center.
All organizations including governmental agencies who consume more than 6000 MWh in 2008 are required to participate. The mechanism is expected to go live in April 2010. Please keep in mind that this consumption requirement is called out as MWh and not Megawatts. What’s the difference? Its energy use over time for your whole company. If you as a data center manager run a 500 kilowatt facility you account for almost 11% of the total energy consumption. You can bet you will be front and center on that issue. Especially when the proposed introductory price is £12/tCO2 (or $19.48/tCO2). Its real money. Again, while not specifically focused on data centers you can see that they will be an active contributor and participant in the process. For those firms with larger facilities, lets say 5MW of data center space – dont forget to add in your annual average PUE – the data centers will qualify all to themselves.
For more information of the CRC you can check out the links below:
- A Good Deck with a high level overview can be found here
- The wikipedia definition
- For alot of additional detail the CRC user guide is a great tool
While many of you may be reading this and feel poorly for your brothers and sisters in Great Britain while sighing in relief that its not you, keep in mind that there are already other mechanisms being put in place. The EU has the ETS, and the Obama Administration has been very public about a similar cap and trade program here in the United States. You can bet that the US and other countries will be closely watching the success and performance of the CRC initiative in the UK. They are likely to model their own versions after the CRC (why invent the wheel over again, when you can just localize to your country or region). SO it might be a good idea to read through it and start preparing how you and your organization will respond and/or collect.
I would bet that you as a Data Center Manager have not been thinking of this, that your CIO has not thought about this, the head of your facilities group has not thought about this. First you need to start driving awareness to this issue. Next we should heed to a call to arms.
One of the items that came out during the Roundtable discussions was how generally disconnected government regulators are to the complexities of the data center. They want to view Data Centers as big bad energy using boxes that are all the same. When the differences in what is achievable from small data centers to mega-scale facilities are great. Achieving PUEs of 1.2x might be achievable for large scale Internet firms who control the entire stack from physical cabling to application development, banks and financial insitutions are mandated to redundancy requirements which force them to maintain scores of 2.0.
Someone once decried to me that data centers are actually extremely efficient as they have to integrate themselves into the grid, they generally purchase and procure the most energy efficient technologies, and are incented from an operating budget perspective to keep costs low. Why would the government go after them before they went after the end users who typically do not have the most energy efficient servers or perhaps the OEMs that manufacture them. The simple answer is that data centers are easy high energy concentration targets. Politically going after users is a dicey affair and as such DCs will bear the initial brunt.
As an industry we need to start involving ourselves in educating and representing the government and regulatory agencies in our space. While the Green Grid charter specifically forbids this kind of activity, having a Data Center industry lobby group to ensure dumb things wont happen is a must in my opinion.
Would love to get your thoughts on that.
/Mm
LooseBolts 
I’m based in the UK and spend a lot of time helping senior managers at major companies to understand the new CRC legislation. You are right to identify that very few people understand or know this legislation is starting in April 2010. I think people managing data centres are going to have the shock of their lives when they work out that the government will be imposing a year-on-year reduction on the amount of electricity they can use. The era of unconstrained energy growth is over!
If you would like more information I’m doing a presentation on CRC at the Bicsi conference in Dublin 17:00-18:00 on Tuesday 23 June. John Dwyer from Microsoft is also speaking about the Next Generation data centre earlier in the day.
Hi Mike,
You write “Achieving PUEs of 1.2x might be achievable for large scale Internet firms who control the entire stack from physical cabling to application development, banks and financial insitutions are mandated to redundancy requirements which force them to maintain scores of 2.0. ”
With free cooling, following ASHRAE recommendations on cold aisle temps, hot air containment, and good UPS selection you can do *much* better than 2.0 with no compromise in reliability. So it’s a myth that reliability and efficiency are in conflict. True, maybe you can’t (yet) get bank-like reliability at a PUE of 1.2 but you can certainly reach 1.5.
-Urs
Urs –
From a pure technology perspective I completely agree with your statement. I would also agree with your statement that efficeincy and redundancy are not necessarily in conflict but do impact each other. I guess where I would potentially see a challenge would be along three lines. First is that the number of banks doing new builds or retro-fits today is fairly small to none. The application of new UPS and other systems would require some re-configuration in facilities that at best where built about 10 years ago or more. With economic conditions being what they are, most banks (and most companies for that matter) are going to try and sweat their assets for as long as they can. Second is that you and I have deeply studied and focused on this space and have stressed technology to its limits to see how far you can really push. The conservative “culture” of most financial organizations would find these general approaches pretty risky. Its an assessment of how much business risk you are willing to take on. I tested this just recently with conversations with a few banks. I think this regulation stuff is going to put that to the test so it will be interesting to see how that changes the balance between risk and efficiency. My last point will probably get me in trouble with some folks, but building data centers is not necessarily core for banks. They instead rely upon a business eco-system which will interpret their needs and drive them to higher levels of Tier, redundancy, reliability, technology or whatever resulting in padding upon padding. If you combine this last point with the culture of convervatism that pervades most organizations, achieving that PUE of 1.5 will be tough. I beleive (and would bet you do to) with a strong operational team driving methods of procedure and standardization of approach and a design with concurrent maintainability you can achieve the same reliability targets. You have touched on one of the reasons why I moved. This stuff needs to get out. Great hearing from you.
\Mm
I think hell just had a coldfront come through and has frozen solid. I am definitely going out and buying a megamillions ticket.
I cannot beleive I am seeing cordial thoughtful and open dialogue between the person driving Google’s data center vision and the guy who built the Microsoft program and set its direction. It is great dialog though. Keep it up.
~Henri
Hi Mike.
Nice post! I have a blog post coming out tomorrow that will point to it.
Would love to know if you’ve gotten any feedback from anyone in the industry thus far in regard to your call to arms.
Thanks,
Ted
Ted, I have had a couple of folks reach out to me on it. But nothing I would say concrete just yet.
Mike,
While the DC guys will definitely be front and center due to consumption, what role do you see evolving inside of large companies that will manage, report, etc on company wide power consumption and carbon credits?
Thanks.
John
Hi Mike,
Very interesting post and well explained. I am in the UK and run a software company developing product that focuses on monitoring and managing data centre energy consumption. We are in the Carbon trust Incubator programme. I agree that the CRC is probably the first of much more legislation in this area and it will not be retricted to the UK / EU.
What were your findings on awareness levels of CRC in the UK, let alone elsewhere, and preparedness for complying?
It seems to me from conversations I have that
(a) knowledge of CRC and what to do about it is fairly low, but growing;
(b) useful monitoring of PUE is low (by useful, I mean monitoring in real time and automatically, as opposed to the annual or 6-monthly clipboard and ammeter approach that seems to be the most common at the moment);
(c) there is a lack of metering technology installed (especially intelligent, network addressable meters) in many facilities and a certain reluctance to invest in this based on perceived cost and risk of downtime.
Thanks,
Philip
Dear Mr. Peterson,
The holistic Data Center need of monitoring and controlling PUE is spot on. For the last several years it has been very evident of the need to do this and the reasons today are more than just bragging rights. From our experience “the action or inaction, supported by the data and either implemented into the process or ignored” is the “achillies heel” of most data centers and operators.
While the power generation and general utilities have been working to maximize electrical performance efficiency, the data center industry has vitually ignored the need to consider these same systems and how they can work to the benefit of the data center. The controls and systems to do this have over 50 years of field application and operate flawlessly.The companies who own, design and operate these data facilities, pay little attention to what is available or the needed MOP’s to achieve and maintain the integration that is necessary. They seem far removed from what is possible. I would love to discuss the causes of the issues, but I will spare you what many of us already know.
From my point of view, there are at least 5 fundamental components for a working solution, that simply dont exist in the majority of the projects and there certainly are more that can impact the result.
1. Standardized Integration and control
2. Electrical application and engineering modeling
3. Standardized equipment and material management
4. ECO-Planning with a -Holistic total approach.
5. Integrated systems technology and advanced product knowledge
Each one of these items is a topic unto themselves and I would be more than happy to discuss.
Each piece listed is an ounce of prevention to ward off the one pound cure. The cure to correct or improve a PUE. More than anything else is having the correct talents, skills and technology to recognize that a negative perfomance shift has taken place and then find a solution to correct it quickly. In a 50 Megawatt site, a one hour delay in correction starts costing major dollars as your load increases.
This is a very difficult feat to accomplish and even adding the meters only tells you that something went wrong after the fact and that is only a lucky hint that something is out of whack.
My thoughts are that the average facility manager and operator won’t have the knowledge or local resources to recognize or diagnose, let alone correct PUE impacting events from mundane maintenance carelessness, to major undiagnosed faults and over time the facility load just creeps up. This is right at the heart of Data center operations, but happens all the time and it is going to be very interesting as to what systems and who will step up first.
I would like to suggest for the IT industry to look to non IT Industry such as heavy equipment, mining, heavy manufacturing for high efficiency, clean solutions that already exist and require minor adaptation for huge performance gains in the data center world.CRC will change the focus of data center development dramatically, but a huge shift must take place in the thinking of the people in charge or the CRC implementation will be very costly and painful. The shift I am talking about is the leading companies of 2011 will be earning carbon credits not paying for them. It is a secondary market and revenue stream, for those that really change the mind set and take advantage of it.
I think the move in the CRC direction of PUE management is going to be very slow for some companies and likely require new dedicated management to get it rolling. All pieces, not just servers, are part of the total PUE and both directly and indirectly impact the PUE. This is going to take some broad technical knowledge to really pin down the causes and solutions.
I also believe that new products need to be put to work, Higher performance heat transfer allowing less energy consumption for cooling, better use of environment functions that are area dependant, smaller data centers and de-centralizing, viewing the network system as a whole and identifying the isolated demands and then supporting these demands with other components, processes, and system approaches. Cloud based component manufacturing will be quicker to adopt and easier to adapt to the changes, that are coming. All these items, will be a huge step in the right direction at reducing carbon.
The companies doing the things I mentioned may be setting the pace of future data center development. This will be easy for some, take time for others, and like we have just seen, working together towards integrated solutions.
Thanks for the great article to stimulate the mind.
James Longacre
Mike
I read your blog with interest and have been tracking your work at Microsoft for some time through various channels which I found to be fascinating and to which I applaud from an efficiency perspective. I work at the Carbon Trust and have been working with the British Computing Society around the creation of a data centre cost and carbon simulation tool – I believe you may already have a dialogue with Liam ?
Anyway, the simulation tool is now at v 0.7 beta ( BCS DCSG members only ) and we have opened up an EOI across the supply chain for DC owner and operators / Manufacturers and Suppliers / M&E and IT consultants to work with us during the next stage. I was wondering if you have taken a look at the tool yet and whether DRT would be interested ? As you will see the tool is actually a framework for supply chain engagement with the providers of components throughout the technology stack which make up the data centre – it is envisaged that the industry will see this as an opportunity to describe their components in an accurate way for use within the simulator.
Perhaps we could meet up at our HQ in London next time you are in town? As a well respected figurehead within the industry it would be good to get your support for this development in some shape or form.
I’m not sure about blog etiquette so rather then posting telephone numbers / e-mail I can be contacted through the Carbon Trust HQ in London if you’re interested.
PS As a former geologist I remain perturbed by the implications and parallels of rapid increases in CO2 emissions from the geological record and what is happening today ( particularly the ‘big one’ – see link below ) – this often helps me focus on the job at hand and the mountain which needs to be moved if we are to avoid something similar.
http://en.wikipedia.org/wiki/Permian%E2%80%93Triassic_extinction_event
Rob Jones
ICT Sector Manager
I am a Green Grid member and was at the inaugural European meeting in London a few weeks ago. At that meeting we were warned to be careful about using PUE to compare data centres in different geographical locations as the metric does not take into account local climatic conditions. Particularly in UK where we have ‘weather’ rather than a ‘climate’ the metric is of particular concern. PUE is only intended to allow year on year comparison of performance at the same site. Of course The Green Grid are very aware of this limitation and are working hard to enhance the metric. I am worried when people start using PUE to compare data centres on opposite sides of the planet.
Andrew
Mike
You make an excellent point regarding the need to educate government. It would be a simple option for them to point at the large data centers, and make a demand for energy reduction.
Our business is open source Green IT evangelism. We try and communicate to small business owners that energy efficiency should be part of their decision criteria.
We believe that small and medium businesses have a key role to play in reducing the total US ITC energy demand, and that they can do this by making good decisions rather than making large capital investments.
PUE is important for the large data centers, but I think it will be price incentives and education on cloud alternatives that influence our 26 million less efficient users.
Being a member of both TGG Tech Comm, Uptime and (one of the) stake holder(s) for the European Code of Conduct I have my own additional view on PUE.
“The best way to improve your PUE is to switch on comateuze servers”
This is obviously the wrong way to improveme the efficiency of your datacenter.
But, what does this tell us?
A: Were missing an element, because a good PUE with a high or even increased energy usage on the Grid connection cannot be the aim.
The element is the overall energy used by the Datacenter (many times known as Grid usage)
It is important to investigate the status quo of the IT Energy usage (kWh), implement your efficiency measures while observing outside temp extremes during that period of implementation.
Depending on the type efficiency implementation works you may see a decrease or increase of PUE but, you should see your Grid usage go down.
If this is not the case while implementing during a same average outside temp, you know that something went wrong.
So, measuring PUE, teasing each other with good indicators will continue to improve ourselves.
Without PUE, there would not have been much of Energy efficiency implementation ongoing.
Only by those ho were aware of the impact before it started.
Lex
Lex,
As always your are right on the money. Cant say I disagree with you at all. PUE has done wonders in changing the conversation and focusing our attention on the right things. Although as my latest post points out, I think we can go farther there.
\Mm
Great post. I’ll be keeping a close eye on our peers in the UK and EU to see how they fare under government CO2 regulation. I agree that its only a matter of time before we see some version of that here. Although the Aussies are giving me some hope. They seem to be giving themselves a reality check regarding the accuracy of the scientific data suppporting man made global warming.
I quoted you in my blog post on the subject:
http://tinyurl.com/ma8wwz
Mike, once again you’ve outdone yourself,
My question or concern depending on how you look at things is what is the EU and the US using to define what a Datacenter is or will be, and when it will get placed into this CO2 tax category? I help run a lot of small “data centers” 1 and 2k sqft types…. but if you add them all up I could get to a single large DC… problem is I’m not allowed to combine them by Government regulations… if they do start taxing at a certain size or energy level would larger DC’s start to create smaller ones to avoid the tax or would it still be cost effective to have a single larger one? where do you see this going?
Thanks
Well in terms of direct action, I think the risk is very little that there will be Data Center specific taxation or regulation in the near to mid term. The more immediate challenge is that at a company level you will be assessed on your total Carbon output. This would include things like travel, energy consumption for lighting, and of course data centers. Essentially you need to think more holistcally. As a result, it would not matter if you had 1 twenty megawatt facility or 20 one megawatt facilities. So the size of the facility or number of facilities would not matter, its the electricity consumption combined with the carbon emission factors of the areas where the facilities reside that will come to play.
Hope that helps
\Mm