Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Data Centers Prepare for a Renewable Future

kdawson posted more than 4 years ago | from the less-facebook-guilt dept.

Earth 97

miller60 writes "A small but growing number of data centers are generating renewable energy at their facility, despite challenges with cost and scalability. In a special report, Data Center Knowledge looks at data centers implementing on-site solar power, wind energy, geothermal cooling and recycling waste heat from their hot aisles. Even as some projects choose to go green, other data center operators insist that improved power efficiency offers a far better return and carbon impact than pursuing on-site renewables."

Sorry! There are no comments related to the filter you selected.

Computing power per watt (2, Insightful)

Yvan256 (722131) | more than 4 years ago | (#32891816)

Use the hardware that give you the most "computing units" (targeted to your computing needs, i.e. floating-point, database access, etc) per watt. That should automatically take care of not using wasteful (heat-producing) hardware.

Re:Computing power per watt (2, Insightful)

girlintraining (1395911) | more than 4 years ago | (#32891950)

Use the hardware that give you the most "computing units" (targeted to your computing needs, i.e. floating-point, database access, etc) per watt. That should automatically take care of not using wasteful (heat-producing) hardware.

There are trade-offs there as well. -_-

except of course, when you leave it idle. (1)

Colin Smith (2679) | more than 4 years ago | (#32892040)

or have all the systems running at 50% capacity.

Re:except of course, when you leave it idle. (2, Insightful)

Yvan256 (722131) | more than 4 years ago | (#32892084)

Idle means zero computing units and running at 50% capacity means half the possible computing units (but probably way more than 50% power usage).

Well, not exactly (2, Informative)

Colin Smith (2679) | more than 4 years ago | (#32892442)

Idle means zero computing units and running

Performance per watt is almost always calculated running flat out at 100%.

So if it's idle. i.e. not doing anything useful, it's almost certainly still consuming a significant amount of power doing symbiotic processing; processing which is necessary to keep the system running but which doesn't contribute directly to useful computing units. Except that won't be covered in the performance/watt figures.

So, using performance per watt when purchasing is really only useful as a measure if you're able to keep your systems running at high utilisation and switch them off otherwise.

 

Re:Well, not exactly (2, Interesting)

poetmatt (793785) | more than 4 years ago | (#32892596)

do you mean symbolic or symbiotic? I can't exactly find that term if you mean symbiotic.

Meanwhile, I agree about performance per watt but I do not agree about idle wattage. It's been shown that for many processors idle wattage is quite low in comparison. In fact, complete computer systems tend to use exponentially more power as they head closer to 100% load or above.

Re:Well, not exactly (1)

Hylandr (813770) | more than 4 years ago | (#32892760)

Lets not forget Screensavers or things like BOINC running when not in direct use.

The best energy policy for these machines is no BOINC or other background operations and blank the screen when not in use.

- Dan.

Re:Well, not exactly (1)

poetmatt (793785) | more than 4 years ago | (#32906628)

well, given that we're talking data centers would they ever really run boinc? That sounds contrary to what a data center would od really.

Re:Well, not exactly (0)

Anonymous Coward | more than 4 years ago | (#32911982)

He certainly meant symbiotic. Symbolic makes no sense in context, and he did explain what he meant by the term.

Re:except of course, when you leave it idle. (1)

Bengie (1121981) | more than 4 years ago | (#32893026)

you build out to support peak usage. Average server usage can be quite low, but you can't have your system coming to a crawl when peak hits.

Re:Computing power per watt (2, Insightful)

skids (119237) | more than 4 years ago | (#32892746)

I'm all for more efficient hardware systems. They definitely, definitely should be done, as long as the efficiency gain is more than incremental. However the danger with taking that approach only is that it encourages rampant expansion as software engineers hear stuff like "we can do twice as much per watt now" and think "goody, I can save several man hours by not compiling out the debug code and re-testing the optimized code."

Same goes (kinda) for virtualization. It's a great technology, very smart, and definitely should be done, but it needs to be kept in mind that in the majority of cases the core reason behind doing virtualization is that you need to run software that is too crummy to share a machine with other software. Virtualization's downside is it becomes an excellent excuse for not applying pressure to your software vendors to get their product up to snuff.

Recycling waste heat is a very good thing. Solar and wind need to be grid tied for IT use because they are intermittent. If the IT staff is actively involved in the energy system, it can offer an incentive to optimize systems and software -- the same way the instant-mileage meter on newer dashboards encourages leaner driving. However if the IT staff isn't invested in the idea they don't really care whether they can stay within the power budget. In fact in most cases, they never see the electricity bill themselves -- it isn't an IT budget item.

So the reasons to "go green" on a data-center level (as opposed to the whole office space) is purely psychological. Not that it isn't a good one, just it merely serves to psychologically invest the IT team.

Re:Computing power per watt (1)

Jurily (900488) | more than 4 years ago | (#32893156)

However the danger with taking that approach only is that it encourages rampant expansion as software engineers hear stuff like "we can do twice as much per watt now" and think "goody, I can save several man hours by not compiling out the debug code and re-testing the optimized code."

Make it run, make it correct, make it fast. As long as developer time is extremely more expensive than CPU time, there won't be time for step 3.

Businesses only optimize for power usage when it's the most expensive factor in the equation. I think we'll have to run out of oil before that happens.

hrm. (4, Insightful)

Anonymous Coward | more than 4 years ago | (#32891826)

"other data center operators insist that improved power efficiency offers a far better return and carbon impact that pursuing on-site renewables."

These are not mutually exclusive.

Re:hrm. (3, Insightful)

eln (21727) | more than 4 years ago | (#32891986)

Exactly. Any data center engineers running into issues with the cost of power and cooling (ie, all of them) should be exploring both of these options. Whatever solutions we come up with, be they efficient machines or renewable on-site energy or both, are destined to become inadequate at some point as our computing needs inevitably expand to fill the available capacity. The more additive solutions we can pile on, the longer the time horizon before we end up in another crisis where we have to find yet another innovative solution.

Re:hrm. (2, Insightful)

Monkeedude1212 (1560403) | more than 4 years ago | (#32892362)

While true, the limitting factors usually boil down to either apathy for the problem, not enough money to deploy all solutions, or the profit motive.

Re:hrm. (2, Insightful)

XanC (644172) | more than 4 years ago | (#32892562)

Not, gasp, the profit motive! The only good datacenter is the one in business to NOT make money, that's what I always say.

Re:hrm. (1)

Monkeedude1212 (1560403) | more than 4 years ago | (#32892680)

Well - okay - its not the profit motive directly, but I can spell out what I meant by that.

You can say capitalism is always the way to go no matter what - but until being green is the best way to make money - you won't see a corporation being green.

There are two ways to change that - by Law (which would be considered government regulation, so not very capitalistic) or by 'voting with your dollar'.

Until the public puts greater emphasis on having green products, by willing to spend more for a green product, (much like how they are willing to spend more for brand name, or even organic food!), than it won't come around.

So no, the profit motive is not the reason exactly, but the way things are right now, its not profitable to be green, and the issue comes up on how that should be changed. Essentially, by a Law proposed by the government or at the consumer level, both ways are democratic.

Re:hrm. (2, Insightful)

Kjella (173770) | more than 4 years ago | (#32892526)

are destined to become inadequate at some point as our computing needs inevitably expand to fill the available capacity.

Which is why you can question how "green" these projects really are, what's the point to reduce consumption if it's immediately offset by an equal and opposite increase in consumption? It's as if we made cars with twice the MPG and everybody decided "cool, then I can make my commute twice as long and really get out of the city". Green projects are those that reduce aggregate consumption, sure it's nice if people get more for each watt or more people are able to participate in the wealth, but it doesn't do the environment any good if the total stays the same or goes up.

Re:hrm. (1)

Monkeedude1212 (1560403) | more than 4 years ago | (#32892772)

Which is why you can question how "green" these projects really are, what's the point to reduce consumption if it's immediately offset by an equal and opposite increase in consumption?

It can be difficult to increase consumption though - at least practically.

Like the car analogy, I can technically drive further on a tank of gas but thats less time I have for my vacation.

Often times there are more factors limitting the consumption than there are limitting efficiency. You can't just decide to run twice as many computers in a building that is already full of computers.

Re:hrm. (1)

dakameleon (1126377) | more than 4 years ago | (#32894732)

That is assuming you're looking only for a net benefit to the environment. In this case, the green tech offsets the added capacity which is used for added productivity elsewhere in the economy. You're allowing for more efficient growth, and the net benefit is that the environment wasn't harmed more in the pursuit of growth.

Yes, idealists will argue that we should fix the environment first, but a pragmatist has to recognise that everyone's going to ask along the chain, "what's in it for me?". This way you've paid the solar/wind/geothermal guy so he can go reinvest capital elsewhere, and you've added productive capacity without causing harm. Showing we can stabilise the environment while growing the economy is probably going to the strongest argument for getting sceptics on side - it becomes much more of a "why wouldn't you?" pull than a "you must because" push.

Re:hrm. (1)

Attila Dimedici (1036002) | more than 4 years ago | (#32892796)

"other data center operators insist that improved power efficiency offers a far better return and carbon impact that pursuing on-site renewables."

These are not mutually exclusive.

They are saying that for all practical purposes they are. There is only so much money that a company can afford to invest in building the data center. If I spend $10,000 on generating electricity from renewable sources and that electricity would only have cost me $5000 over the life time of the data center, that is $10,000 I don't have to spend on more energy efficient equipment in the data center. (I am using an example which shows a tradeoff that would make renewable energy a bad decision, not one that I have any idea if it is realistic).

Re:hrm. (1)

evilviper (135110) | more than 4 years ago | (#32894284)

These are not mutually exclusive.

...if you have unlimited funds at your disposal.

Re:hrm. (0)

Anonymous Coward | more than 4 years ago | (#32900382)

depends on their budget

This obseesion with efficiency (2, Insightful)

countertrolling (1585477) | more than 4 years ago | (#32891882)

It makes for very delicate, frail, some times dangerous products. Stone age equipment running on renewables is much more robust on the long term.

been there, done that (2, Interesting)

Anonymous Coward | more than 4 years ago | (#32891910)

My (small) datacenter is 100% off-the-grid solar powered (with redundant power feeds from two PV systems), and I recycle the waste heat.

It wasn't particularly "difficult" or "expensive", but a good example of what's possible when you *really* care about solving the problem.

Re:been there, done that (1)

Monkeedude1212 (1560403) | more than 4 years ago | (#32892080)

How Small is your data center though - and how does the density compare to larger datacenters?

I think the issue is that you found a great way to pack 100 servers in a room and keep it off the grid. Whereas companies like Microsoft have managed to fit 1000 servers in the same space and to deploy these green systems requires more space than what their building allows.

Re:been there, done that (0)

Anonymous Coward | more than 4 years ago | (#32892126)

And the proof for any of this is where?

id like to see (3, Insightful)

nimbius (983462) | more than 4 years ago | (#32891962)

exactly how much in the office, not the datacenter, we're failing to "go green." I know its off topic but aside from the lights-out datacenter not much has really been done for large datacenters like the one i work in, while the office seems like an energy hog with no end in sight

I do hear constantly however of minimum light levels that must be maintained in offices, and the temperature in a cube farm being forcibly maintained at 72 degrees. the vending machines run 24/7 when nobody is around, and the parking lot is constantly lit up like a runway.

Re:id like to see (3, Insightful)

jridley (9305) | more than 4 years ago | (#32892158)

I agree, it's pretty damned inefficient here. They build buildings with the cheapest construction techniques available, just basically a big metal semi-insulated crackerbox, then put 10,000 tons of A/C on the roof. There are 45,000 watts of fluorescent tubes just on this floor of our office building, and they're on for hours a day that are not necessary. I'd like to be able to turn my computer off, but every few days I need to access it remotely. I could do both if they'd deploy a little 50 watt wake-on-lan box, but nobody cares. I have asked about 10 times over the last 5 years for the "green team" to push for "put the monitors in power save mode after 30 minutes" to be the default on the standard desktop, but though they always say "that's a great idea" it never happens.

Re:id like to see (1)

h4rr4r (612664) | more than 4 years ago | (#32892336)

Why do you need an extra box? Just about all office computers made this decade support wake on lan.

Re:id like to see (2, Insightful)

icebraining (1313345) | more than 4 years ago | (#32892536)

Wake on Lan doesn't work remotely, because it works below the IP layer (a disconnected computer can't have an IP address, since the TCP/IP stack isn't running).

Re:id like to see (1)

h4rr4r (612664) | more than 4 years ago | (#32892788)

No, you need to vpn in then login to a machine that does stay up and use it to send the wake on lan packet.

Re:id like to see (1)

h4rr4r (612664) | more than 4 years ago | (#32892814)

To make it clearer, you can just pick 1 machine per row or floor or even better a small linux vm with no other use.

Re:id like to see (2, Insightful)

icebraining (1313345) | more than 4 years ago | (#32893808)

And that 1 machine is the box he's talking about. With the difference that the "box" would use much less power.

Re:id like to see (1)

h4rr4r (612664) | more than 4 years ago | (#32908748)

Than 1 vm that only sends out wakeups? I highly doubt it.

Re:id like to see (0)

Anonymous Coward | more than 4 years ago | (#32914716)

Yeah, his problem is he needs someone to set it up. Not that he doesn't know what needs to be done.

Re:id like to see (1)

nomorecwrd (1193329) | more than 4 years ago | (#32892618)

Because he needs to reach his PC and "tickle" it using it's MAC number.
And usually the office runs in a LAN, and the PCs are not directly visible from the outside. Hence you need a little box that handles both network interfaces (to be seen by the internet and able to see the LAN) to forward in the magic packets.

Re:id like to see (1)

h4rr4r (612664) | more than 4 years ago | (#32892824)

So you vpn in, rdp/ssh to a machine left up for this purpose, preferably a vm that can be run on a server for near 0 cpu cost since it so rarely gets used. This lets you launch the wake on lan packet for this purpose.

Re:id like to see (1)

jridley (9305) | more than 4 years ago | (#32901870)

Yup, and that's the box I was talking about. I'd prefer for them to put together a low power PC and just leave it in the server room to do this for a whole floor at once.

This is why I have shares in energy companies (1)

Colin Smith (2679) | more than 4 years ago | (#32892544)

Human nature. People are one or more of apathetic, complacent, lazy and stupid. It's great.

 

Re:id like to see (2, Funny)

JumpDrive (1437895) | more than 4 years ago | (#32893944)

Well you are lucky that you aren't here. Here they installed the double pained reflective windows backwards, so light comes in and you can always see your reflection. But at least it is double pained glass.

Re:id like to see (0)

Anonymous Coward | more than 4 years ago | (#32915990)

Here they installed the double pained reflective windows

That must hurt.

Re:id like to see (2, Interesting)

Bryansix (761547) | more than 4 years ago | (#32892300)

Effecient Office design can be good but it can have it's drawbacks. For instance, we are in a suite of a larger office building that was once part of another suite. They built walls but they did not install a 24/7 A/C unit for our server rack. Instead we operate a floor model which emits it hot air into the drop ceiling thereby causing further ineffeciencies. So yes, effeciency is good but good planning and scalability and flexability are sometime more important.

Re:id like to see (2, Funny)

Wiarumas (919682) | more than 4 years ago | (#32892554)

Be careful what you wish for. I worked in a building where the client refused to turn on the lights on a floor that had contractors. That was miserable - especially in the winter when I went to work, it was dark, dark all day long, and went home and it was dark. Green, but miserable.

On a more positive note, they also promoted working remotely which was one of my favorite perks about that place.

Re:id like to see (0)

Anonymous Coward | more than 4 years ago | (#32893024)

Doesn't have to be that way: http://www.nrel.gov/sustainable_nrel/rsf.html

The RSF uses technology that any office building could use. Natural lighting, passive ventilation, and fairly strict energy budgets for office workers (but the main thing is just turn off the stuff you aren't using when you leave your desk! And each desk includes a "power off" button for that purpose)

Re:id like to see (1)

Luke has no name (1423139) | more than 4 years ago | (#32910344)

At our workplace, we're mandated to leave our desktops ON 24/7 because "you never know when the Desktop team is going to push out software updates".

Green Institutions (1)

stagg (1606187) | more than 4 years ago | (#32891964)

I found this interesting and pertinent. I work at an institution that's extremely interesting in "going green" as they have a large, growing IT department with their own data center and like to think of themselves as being "progressive." Does anyone have any further information on this kind of project? Preferably something that dodges the buzz word bingo game and is actually constructive, rare as that may sound.

Re:Green Institutions (2, Interesting)

codepunk (167897) | more than 4 years ago | (#32892564)

Any how many of their workers telecommute, imagine if all of them did, savings of probably 100's of tousands of gallons of gasoline not burned. I often imagine how much gasoline could be saved in this country if nearly every office worker in the country that was able to, could telecommute the majority of the time.

Re:Green Institutions (1)

raind (174356) | more than 4 years ago | (#32892650)

I hear that, not much reason to be in the office besides the occasional hardware problem, power failure, or when some miscreant throws a large rock thru the window to steal a flat screen tv.

Re:Green Institutions (1)

ducomputergeek (595742) | more than 4 years ago | (#32892792)

We had some excess profits back in 2007 that was use or be taxed at 40% so we put up some solar panels. (Also some tax credits at the time at the state level that made it attractive as well). We're a small shop, but invested about $60k all said and done and it cut our utility rates per month to cover a Jr. level developers salary. In fact we were planning on using the savings to hire an additional developer, but that didn't happen due to the economy. Also, last year the state adopted a new law that allowed us to choose our electricity provider. The savings from that would have come close to reducing our power bill about the same amount as the solar panels. Under the old utility rates, ROI would have been about 8 - 10 years. With the new rates it's more like 12 - 14 years.

If we had it to do over again, we would have been better of to have paid the tax and have had the extra cash on hand honestly.

Re:Green Institutions (1)

c6gunner (950153) | more than 4 years ago | (#32892984)

So a junior developer only costs $6,000 a year? Wow. I knew computer jobs don't pay as much as they used to, but that's just ridiculous.

Re:Green Institutions (1)

Lodragandraoidh (639696) | more than 4 years ago | (#32903508)

Add another zero there cowboy.

Re:Green Institutions (1)

c6gunner (950153) | more than 4 years ago | (#32906352)

If the ROI is 10 years, and the investment is 60k, I think my zeroes are all accounted for.

Re:Green Institutions (1)

MindSlap (640263) | more than 4 years ago | (#32893088)

Forget about the 'language'.
The hippy 'green', 'progressive' shit isnt gonna work.
(Well..progressive shit never works anyway).

But as far as power consumption goes...do it in BUSINESS TERMS.
Begin with..."This will save us money".
Its as simple as that.

When I consolidated a bunch of remotely accessed PC's into a VM environment, I didnt present 'hippy crap'. I submitted a spreadsheet that laid out the power consumption numbers, cost of equipment, licensing etc. It was pretty comprehensive. Even included 'pretty graphs' for the higher ups.

They listened. I built it.

Lesson:
If all your gonna do is 'be enlightened' and sing of unicorns, rainbows and greenie-weenie garbage, you should just quit your job and live in a commune.

In the real world, you'll achieve much more with a complete idea/plan rather than leg humping algore.

Re:Green Institutions (2, Interesting)

jbengt (874751) | more than 4 years ago | (#32894926)

I didnt present 'hippy crap'. I submitted a spreadsheet that laid out the power consumption numbers, cost of equipment, licensing etc. It was pretty comprehensive.

I don't think you understand that 'hippy crap'. I've worked on construction projects where the "hippy 'green', 'progressive' shit 'language'," as you say, was important. Green design effort includes the sorts of things you put in your "pretty comprehensive" spreadsheet, but also includes the impacts of various possible combinations of walls, roof, glass, lighting, energy sources, HVAC system types, plumbing equipment, etc. It includes 365-day simulations of hourly energy costs using hourly data on weather, solar, internal loads, energy rates, etc. for different systems, usually including a base of minimum code requirements vs a few other possibilities. The "hippy, green language includes comparisons of capital costs and operating expenses, often on a present value basis. You may be surprised, however, how many owners are just as interested in "going green" as in the "bottom line" costs of the project. To me, that shows that there is currently a perceptible value in going green that should not be ignored.

Re:Green Institutions (1)

MindSlap (640263) | more than 4 years ago | (#32898920)

Then..quite frankly..I wouldnt want to work where you work... Why? Because I'm interested in the bottom line....not hippy crap.

Re:Green Institutions (1)

jbengt (874751) | more than 4 years ago | (#32908214)

Let me emphasize the point I was trying to make.
The bottom line and the green hippy crap are pretty much the same. If you can't prove the savings, it's not really all that green.

However, the projects that go green are interested in long term savings.
Many other projects are only interested in the lowest construction cost. Sometimes that's because someone else is paying the long term costs. Sometimes that's because long term costs don't matter if you go bankrupt trying to pay the short term costs.

Re:Green Institutions (1)

Lodragandraoidh (639696) | more than 4 years ago | (#32903930)

(Well..progressive shit never works anyway).

I suppose it's okay for your 9-year-old child (if you have one) to work in a factory?
Or should we return to the squalor of tenement housing - circa 1900?
Or allow corporations and political machines to run amok as seen in the scandals at the turn of the previous century that make Enron et al pale in comparison.
What about the vote for women?

That is not to say there weren't any mistakes (18th Amendment anyone?) - however, I think the world as we know it, as bad as we may think it is, would be much worse without progress/reform.

Without progress, we would still be drawing on cave walls and hunting wild animals with our bare hands to feed our families. The first time someone broke off a tree branch or fashioned a flint knife to improve his odds of success - progress was happening.

Don't conflate ultra-liberalism with progressivism.

In other news.... (0)

Anonymous Coward | more than 4 years ago | (#32891966)

Companies prepare for higher hosting costs and increased downtime.

Hot hot aisles (1)

Taibhsear (1286214) | more than 4 years ago | (#32892006)

implementing on-site solar power, wind energy, geothermal cooling and recycling waste heat from their hot aisles.

Anyone else get a raging brainer reading this?

More virtual machines and stacked hardware (1)

bigfootchick (1855082) | more than 4 years ago | (#32892008)

Get more virtualization and stacked hardware, the one that sinks in water like they showed a few months ago in /.

You can also try solar powered panels which will use the sun's rays to illuminate the servers and make them more efficient in summer.

To save on costs, you can always use renewable sources of energy like this [xeof.net] .

Time is nigh for room-temp super-conductors. (1)

yargnad (1456405) | more than 4 years ago | (#32892086)

Theres a lot of research in this field ATM and most states that the real revolution will come when we have data-centers that won't need cooling for more than creature comforts. At that point, solar, wind and other "green"(arguably) energy sources will become more feasible for data-centers.

Re:Time is nigh for room-temp super-conductors. (1)

TooMuchToDo (882796) | more than 4 years ago | (#32892490)

Most servers are now warranty rated to have incoming air at 95F. There is no point to air condition DC air (probably still need to dehumidify it though) instead of just bringing inside air in and venting the hot air, unless the ambient outside temp is above 80F.

Re:Time is nigh for room-temp super-conductors. (1)

yargnad (1456405) | more than 4 years ago | (#32892548)

This means the servers themselves will require no cooling internally; no fans = less power draw. Plus every data-center I've been in keeps the Fahrenheits around below 70.

Re:Time is nigh for room-temp super-conductors. (2, Interesting)

h4rr4r (612664) | more than 4 years ago | (#32892848)

No point?
If I turn off the AC and do as you suggest, draw in outside air the room would be up to 110F in a couple hours. Sealed if the the HVAC fails the temp alarms set at 95F go off in 30 minutes.

The low temp in the room gives us time to get the HVAC units fixed if it comes to that.

Re:Time is nigh for room-temp super-conductors. (1)

TooMuchToDo (882796) | more than 4 years ago | (#32892978)

If the ambient air outside is below 80F, you're drawing it in and cooling equipment, and then exhausting it directly outside away from the inlet, you're not going to overheat your datacenter. And if the temperature *is* rising, you're not exchanging air fast enough.

Re:Time is nigh for room-temp super-conductors. (1)

h4rr4r (612664) | more than 4 years ago | (#32893310)

The reality is lots folks can't exchange air fast enough, it would require lots of new ducting, blowers and filtering. Plus some sort of dehumidification. On top of that even here in Buffalo NY the air temp is over 80F. Sure that may not be normal, but if we have to have a real HVAC system 30 days a year then we really can't justify having both methods of cooling.

Re:Time is nigh for room-temp super-conductors. (1)

jbengt (874751) | more than 4 years ago | (#32895004)

If you only need mechanical cooling 30 days a year, you can't really afford to not use economizer ("free" outside air cooling) the rest of the time. OF course, it might be difficult to implement in an existing building, but it'd be well worth trying.

Re:Time is nigh for room-temp super-conductors. (1)

h4rr4r (612664) | more than 4 years ago | (#32908762)

Glycol is the correct solution. In this way you can use the same HVAC that gets used all year and you use the outside your source of cold.

Meanwhile (0)

Anonymous Coward | more than 4 years ago | (#32892166)

"Even as some projects choose to go green, other data center operators insist that improved power efficiency offers a far better return and carbon impact that pursuing on-site renewables."

Some says it tastes great, others less filling.

creators' newclear power puts a new spin on energy (-1, Offtopic)

Anonymous Coward | more than 4 years ago | (#32892216)

the other more efficient than anything we have now energy source is available, but not to us...yet. we will have have to wait until almost everybody is dead (poisoned) so that the corepirate nazi illuminati can feel safe/uncrowded/fulfilled. see you on the other side of it?

meanwhile (might be quite a while); the corepirate nazi illuminati is always hunting that patch of red on almost everyones' neck. if they cannot find yours (greed, fear ego etc...) then you can go starve. that's their (slippery/slimy) 'platform' now. see also: http://en.wikipedia.org/wiki/Antisocial_personality_disorder

never a better time to consult with/trust in our creators. the lights are coming up rapidly all over now. see you there?

greed, fear & ego (in any order) are unprecedented evile's primary weapons. those, along with deception & coercion, helps most of us remain (unwittingly?) dependent on its' life0cidal hired goons' agenda. most of our dwindling resources are being squandered on the 'wars', & continuation of the billionerrors stock markup FraUD/pyramid schemes. nobody ever mentions the real long term costs of those debacles in both life & any notion of prosperity for us, or our children. not to mention the abuse of the consciences of those of us who still have one, & the terminal damage to our atmosphere (see also: manufactured 'weather', hot etc...). see you on the other side of it? the lights are coming up all over now. the fairytail is winding down now. let your conscience be your guide. you can be more helpful than you might have imagined. we now have some choices. meanwhile; don't forget to get a little more oxygen on your brain, & look up in the sky from time to time, starting early in the day. there's lots going on up there.

"The current rate of extinction is around 10 to 100 times the usual background level, and has been elevated above the background level since the Pleistocene. The current extinction rate is more rapid than in any other extinction event in earth history, and 50% of species could be extinct by the end of this century. While the role of humans is unclear in the longer-term extinction pattern, it is clear that factors such as deforestation, habitat destruction, hunting, the introduction of non-native species, pollution and climate change have reduced biodiversity profoundly.' (wiki)

"I think the bottom line is, what kind of a world do you want to leave for your children," Andrew Smith, a professor in the Arizona State University School of Life Sciences, said in a telephone interview. "How impoverished we would be if we lost 25 percent of the world's mammals," said Smith, one of more than 100 co-authors of the report. "Within our lifetime hundreds of species could be lost as a result of our own actions, a frightening sign of what is happening to the ecosystems where they live," added Julia Marton-Lefevre, IUCN director general. "We must now set clear targets for the future to reverse this trend to ensure that our enduring legacy is not to wipe out many of our closest relatives."--

"The wealth of the universe is for me. Every thing is explicable and practical for me .... I am defeated all the time; yet to victory I am born." --emerson

no need to confuse 'religion' with being a spiritual being. our soul purpose here is to care for one another. failing that, we're simply passing through (excess baggage) being distracted/consumed by the guaranteed to fail illusionary trappings of man'kind'. & recently (about 10,000 years ago) it was determined that hoarding & excess by a few, resulted in negative consequences for all.

consult with/trust in your creators. providing more than enough of everything for everyone (without any distracting/spiritdead personal gain motives), whilst badtolling unprecedented evile, using an unlimited supply of newclear power, since/until forever. see you there?

"If my people, which are called by my name, shall humble themselves, and pray, and seek my face, and turn from their wicked ways; then will I hear from heaven, and will forgive their sin, and will heal their land." )one does not need to agree whois in charge to grasp the notion that there may be some assistance available to us(

boeing, boeing, gone.

Is "Web 2.0" really necessary? (2, Insightful)

Animats (122034) | more than 4 years ago | (#32892234)

Maybe the way to cut energy consumption is to dump unnecessary "Web 2.0" junk. Serving static pages is very cheap. Is it really necessary to generate the pages on your site from some "content management system" which makes multiple database accesses just to display essentially the same page over and over?

Re:Is "Web 2.0" really necessary? (1)

fuzzyfuzzyfungus (1223518) | more than 4 years ago | (#32892486)

In any but the smallest and most naive deployments, or situations where pages do, in fact, have to be generated dynamically because they are substantially unique per-user, the use of CMS caching is already commonplace.

In the most extreme cases, the user will actually treat the CMS system, running on an internal dev box, as essentially a glorified HTML editor; an easy way to get consistent style and working navigation links on all the pages you write, and then push the static output of the CMS to the actual webserver. Doesn't work if you want comments; but gives you the advantages of easy layout/navigation/styling and sharply reduces your vulnerability to common CMS hacks.

More commonly, the actual CMS will be online; but there will be some caching of output. Particularly with memory so cheap, hammering the DB every time a new user shows up or refreshes doesn't make any sense at all unless the page has actually changed recently.

Obviously, this is more likely to happen in well managed pro environments than in joe nobody's thrown-together drupal instance; but that's the handy thing: the more users you have(and thus the greater the energy cost of Doing It Wrong), the greater the financial costs of doing it wrong.

That's the nice thing about much(though not all) of IT energy use. The energy market itself is riddled with all kinds of fucked up externalities; but IT energy use is (comparatively) easy to measure, and actually gets allocated pretty accurately; by the standards of a lot of externality-riddled markets. Particularly with the move to laptops, even horribly ignorant consumers have an energy efficiency metric to care about: energy-hungry laptops are hot, heavy, and have short battery lives. Energy efficient ones are lighter, quieter, and have better battery lives. Among serious hosting operations, energy costs are a pretty decent slice of overall hosting costs, so they are watched fairly carefully(and any modern PC whose ACPI implementation isn't seriously fucked can actually report fairly accurately on its own energy use, making fairly comprehensive management and visualization a fairly simple software problem.)

Probably the last area where energy management really still sucks is your basic giant-cube-farm-o'-enterprise-desktops use case(Hardcore gamer kiddies draw more power per capita; but they aren't as common, and much of their energy draw is waste only in the sense that humanity doesn't really need to play Crysis, not the sense that simple settings changes that could have been made weren't). That represents enough computers that it really matters; but WoL is AWOL enough that a lot of IT departments are loath to turn of machines, for fear that they won't be able to wake them for patches, AV updates, and other things best done when expensive workers aren't trying to get work done on them(Plus, centralized power management of XP boxes is surprisingly shit, I had no idea it would be such a pain in the ass before I was involved in a project attempting it).

Re:Is "Web 2.0" really necessary? (1)

dbIII (701233) | more than 4 years ago | (#32894974)

In any but the smallest and most naive deployments

Many places would fit that criteria, usually all you want the client to see is your list of services and contact details. With a lot of detail that's still only a few megabytes of static pages plus whatever images you want people to see.
If you're not actually providing shopping carts, order tracking etc what is going to change daily anyway?

Re:Is "Web 2.0" really necessary? (1)

drinkypoo (153816) | more than 4 years ago | (#32898836)

More commonly, the actual CMS will be online; but there will be some caching of output. Particularly with memory so cheap, hammering the DB every time a new user shows up or refreshes doesn't make any sense at all unless the page has actually changed recently.

Even using good old Drupal you can set up syndication such that whatever you publish to your test server gets syndicated to the published one. You can make it show up on the test page without "publishing" (a checkbox for article state) or you can use some other means to mark articles for syndication, it's easy to add a checkbox to a node type. And of course, even Drupal caches aggressively.

Probably the last area where energy management really still sucks is your basic giant-cube-farm-o'-enterprise-desktops use case [...] centralized power management of XP boxes is surprisingly shit, I had no idea it would be such a pain in the ass before I was involved in a project attempting it

Yeah well, Windows is the problem. If your devices support WoL and you kick off updates from the machines, updating them from a local store (a local repo for Linux, a local WSUS server or whatever it's called now for Windows) then this shouldn't be a big problem. And I can't see how even Windows XP should fail it.

Re:Is "Web 2.0" really necessary? (1)

Stormie (708) | more than 4 years ago | (#32896044)

If this Slashdot article had been a static page, not only would it have been cheaper to serve, but you wouldn't have had the opportunity to post your asinine comment.

Both? (2, Insightful)

2obvious4u (871996) | more than 4 years ago | (#32892270)

Even as some projects choose to go green, other data center operators insist that improved power efficiency offers a far better return and carbon impact that pursuing on-site renewables.

Why is it that everything must be polarized. Why aren't we doing both? Both are good and they are not exclusive.

Re:Both? (1)

h4rr4r (612664) | more than 4 years ago | (#32892388)

Money, you have $X to get $Y compute units and a place to put them. To go green you either spend more on efficiency or green power or some mix of the two. This is way less about environmental green and more about green that you can spend though. Data Centers have always tried to reduce their power bills. Every watt you save is two more you don't have to use for cooling, and a ~1VA you don't need in UPS.

Another Benefit! (1)

www.sorehands.com (142825) | more than 4 years ago | (#32892320)

If you have a lower power draw and solar/wind power, it makes it a bit easier to last though power outages without having to fire up the generator.

Renewable energy sources are too slow. (0, Redundant)

ScentCone (795499) | more than 4 years ago | (#32892626)

A datacenter running on its own renewables would be doing something like growing trees on the roof and then burning them, or using waste heat to drive algae scum units and then oil-ifying them, etc. Otherwise you are harvesting/harnessing other sources of energy (wind, solor) or simply pumping your energy into the ground, which you are thus warming up (geothermal cooling). Wind and solar are not renewable per se, they're merely abundant and not terribly efficient to use.

Imagine (4, Insightful)

codepunk (167897) | more than 4 years ago | (#32892628)

Imagine the fuel savings if every office worker that was able could telecommute instead of burning fuel to get to a job that could be done from home. Imagine the money saved on road maintenance and other things associated with the reduction in traffic. For at least the last 15 years I have commuted back and forth every day to perform a job I could have done without ever leaving my home.

Re:Imagine (1)

Hylandr (813770) | more than 4 years ago | (#32893064)

Imagine also the savings on your wardrobe by not having to dress every day for work.

Makes conference calls a lot more entertaining too.

Just don't get caught snoring on the floor during the latest patent read. :)

- Dan.

Re:Imagine (2, Insightful)

cj_nologic (1649427) | more than 4 years ago | (#32893742)

Imagine the fuel savings if every office worker that was able could telecommute instead of burning fuel to get to a job that could be done from home. Imagine the money saved on road maintenance and other things associated with the reduction in traffic. For at least the last 15 years I have commuted back and forth every day to perform a job I could have done without ever leaving my home.

Most office workers would be incapable of working from home all the time - partly from lack of motivation, partly from lack of social interaction. A lot of face to face meetings are pretty important too, and much as they are laughed at, water fountain conversations are where a lot of personal and business relationships are fostered.

The real alternative would be if people lived close to their offices and walked or cycled in every day. It would improve fitness, but also improve communities. In my country lots of people cannot afford to live close to city centers or business parks where they work, so they live in large housing estates on the edge of the city. This leads to estates where essentially everyone is away all day, everyone spends an hour or two in their cars instead of socialising or spending time with families. Then people spend the weekends in their cars again because suddenly all their friends, shops, social and sporting engagements are long distances away from where they live, and so the estates themselves never achieve a sense of community. And, of course, lots of fuel gets burnt.

I'm not sure how this can be rectified - town planning, perhaps, but it also needs a cultural mind-shift away from the car as the preferred mode of transport. It amazes me to see how people will drive 10 miles to the sports center, cycle 20 miles on an exercise bike in an air-conditioned room under strip lights, then drive 10 miles back. WTF?

Re:Imagine (1, Informative)

Anonymous Coward | more than 4 years ago | (#32894154)

It amazes me to see how people will drive 10 miles to the sports center, cycle 20 miles on an exercise bike in an air-conditioned room under strip lights, then drive 10 miles back. WTF?

So... I'm going to post this anonymously, because I'm one of these people, and kind of embarrassed about it, but I think that behavior is perfectly explainable. I know I need exercise, and I feel better when I get it, but I don't love doing it. So, given the choice between spending 40 minutes on a road bike when the temperature is 90+ outside, and spending 40 minutes on an indoor exercise bike in a nicely air conditioned environment where I can listen to some music... well, I'll take the A/C. If it helps, my exercise room is in my apartment complex, so I at least don't have to drive there, but the larger point stands.

Sorry if I'm not virtuous enough for you.

Re:Imagine (1)

victorhooi (830021) | more than 4 years ago | (#32895906)

heya,

Yeah, I have to say I don't get these people either. Personally, I dislike the idea of gyms for treadmills/bikes, unless there really is no room to run/exercise outside (other sorts of exercise obviously it makes sense).

My bestfriend is like that, I normally hates gyms, but she seems to like the idea of going there to run on a treadmill, yet loathes the idea of jogging for 15 minutes to get to the gym.

Or another friend, I play tennis with her, and she drives - I kid you not - literally 340 metres, around the corner to get to the tennis courts because it's "more comfortable than walking, and I don't want to lug my gear there".

This is Australia, mind you, where in most suburbs, we have nice leafy surrounds, and decent parks to run around in. I've moved to the city recently, and I have to say the running tracks and parks actually suck quite badly here -but I blame the Sydney City council for that. Still, even with our crummy Sydney weather lately, I much rather prefer running outside.

If I could find a decent place to run in the city, I'd much rather run outside, with the sun and wind, than cooped up in a stuffy apartment with lots of other sweaty people around.

Cheers,
Victor

Re:Imagine (1)

minorproblem (891991) | more than 4 years ago | (#32893842)

Hallelujah!! I think this every day when i drive to work. Im an electrical engineer, could quite easily sit at home and create calculation records etc. Instead i drive to my cube farm every day and sit at a computer the whole day.. I probably only have about 20 minutes worth of face to face interaction with other engineers which could quite easily be done with teleconference.

I actually spend more time chatting with other engineers on messenger who are sitting in the cubicle next to me than i do spend chatting with them during the day (I know that is a little sad but its easier than standing up and down and i can send them links easily).

Re:Imagine (3, Insightful)

JumpDrive (1437895) | more than 4 years ago | (#32894020)

This has been going on for a long time. The current problem is that nobody thinks you work when you are at home. Here we have people who actually come in and put their head on their desk, but they are deemed good employees because they show up.

Basically it boils down to management. Usually it is deemed that you have to visually see the people to know they are working, otherwise you would have to know what they are working on to determine whether they are working effectively.

Re:Imagine (1)

pspahn (1175617) | more than 4 years ago | (#32895316)

I, too, generally have to drive 40 minutes each way to work to do a job that I could do quicker and cheaper from home.

It's coming around, though. I have shown everyone that I can access our ancient POS system remotely from my laptop, and can even access (though it's pretty crude because of no keyboard) it from my phone.

Re:Imagine (1)

MtViewGuy (197597) | more than 4 years ago | (#32897862)

While it sounds like a laudable idea, many office workers cannot telecommute because they deal with highly proprietary data or data that if compromised could have serious privacy implications. At where I currently work (the California Franchise Tax Board), any privacy breaches can result not only in your termination, but also could face serious fines AND jail time, too--I have to follow a lot of strict policies in regards to protecting taxpayer data.

An Efficient Office (4, Interesting)

MrSteve007 (1000823) | more than 4 years ago | (#32892790)

I manage and operate one of the more efficient office spaces in the US (I was awarded a National EnergyStar award in 2008 for my work). We've implemented almost everything possible for our small server racks. We've gone from 8 machines to 3 via virtualization, and have a 10kW array and 40kw battery backup for our operation - which now results in zero down time. In doing just that, we've gone from 58 kWh used from the grid a day for our servers to zero (the PV array supports it). Also, instead of using dedicated A/C - we've re-engineered our ductwork to pull in ambient air from the office space, and redirect the hot exhaust to different locations. During the summer, it's dumped directly outside - and during the winter it's used to heat our entrances and used to cover the heating needs of the building at night.

In terms of energy use for the servers and A/C alone, we're saving about $4,000 a year - and that's just for a small server arrangement.

http://www.energystar.gov/index.cfm?fuseaction=labeled_buildings.showProfile&profile_id=1008052 [energystar.gov]

Re:An Efficient Office (1)

h4rr4r (612664) | more than 4 years ago | (#32892890)

So many years would it take to break even?

Not criticizing I would love to do something like that. I am currently trying to go to glycol on the roof for cooling instead of our current dumping water down the drain solution.

Re:An Efficient Office (3, Insightful)

MrSteve007 (1000823) | more than 4 years ago | (#32894466)

While it seems like a shifty answer, it all depends on how you calculate return on investment . . .

Without any tricky accounting, the simple ROI of the PV array is about 12 years. If you calculate the ROI based on the PV and battery backup, factoring lack of downtime, in our case it was closer to an 18 month ROI. For us, each hour of downtime translates to roughly $5,000 of lost earnings. It doesn't take too many hours of backup power to pay off. Of course we could have gone with a gas generator for a much cheaper installation cost, but the tax benefits of a PV array for a corporation can be very attractive.

As for the virtualization, that was based more on the regular 5 year replacement cycle we have on our hardware. Instead of replacing 5 old servers with 5 new servers, it was much more simple and cost effective to build out one powerful machine and virtualize the existing machines.

The cost of the ductwork and fan was about $1,500 - however our A/C unit consumed roughly $1,000 a year to cool the space, so an 18 month ROI. Of course, it's all dependent on your climate, building layout, age of equipment and ease of installation. For us, it's worked out well. We've now achieved a 75% reduction over our baseline from 3 years ago in our grid energy needs, while increasing processing power, lighting levels, and maintaining a comfortable climate controlled office.

http://jbdg.com/results.html [jbdg.com]

Re:An Efficient Office (1)

djdevon3 (947872) | more than 4 years ago | (#32894214)

I really like that idea. Using hot air is easy because there's plenty generated. It's how to use the cold air most efficiently that is the hardest thing to do. Very nice concept. I wouldn't mind reading an article on it. Have you posted the practical application to a blog or something like that?

Re:An Efficient Office (1)

Philomage (1851668) | more than 4 years ago | (#32905408)

You're my hero Mr. Steve. I work in a huge data centre in Canada and it always amazes me to no end when they a/c the data centre to conteract the building heat they're blowing in to keep out the winter cold. It's a hole mess of inefficient. However, it must be pretty difficult to retrofit an ancient and huge data centre.

Being more efficient at Burning Coal, Anyway (1)

CartaNova (1826252) | more than 4 years ago | (#32893946)

In the long run, being more efficient at *burning coal* just isn't environmentally-friendly. DataCenter Knowledge's article follows our own on the Environmental Impact of the Internet: http://cartanova.ca/green-community-blog/item/71-the-environmental-impact-of-the-internet [cartanova.ca] We quote them, so I'm guessing they saw it and posted their article. (although they have an excellent series of pieces addressing this issue already). In short, things don't look so good for the earth these days (but you already knew that :)

Found this story in May and blogged about it, (1)

physburn (1095481) | more than 4 years ago | (#32894912)

blog [blogspot.com] , HP had published an academic paper about combining a data-center and farm, using biomass for local farms to power the servers in your server farm. Note however that transmission line and contenting to a the grid, don't cost very much in terms of efficiency (1 per cent, probably), or electricity price rate (is biomass cheaper than wind or sun, right now? varies with the weather doesn't it).

Run the Data Centers on renewable energy (1)

tryggvil (1855860) | more than 4 years ago | (#32899058)

The only way to solve this in the long run is to address the source of the problem (instead of making use of extra heat or improving efficiency) and make the Data Centers actually run on clean power.

Iceland has the uniqueness of having a 100% reneable electricity power grid (probably the only country?) and there are several Data Center projects ongoing making use of that such as Verne Global [verneglobal.com] .

On top of this infrastructure there is also a startup building what will be the first Truly Green Cloud Computing IaaS service called GreenQloud [greenqloud.com] which actually I am working on.
Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?