Slashdot Mirror


Google's Chiller-Less Data Center

1sockchuck writes "Google has begun operating a data center in Belgium that has no chillers to support its cooling systems, which will improve energy efficiency but make weather forecasting a larger factor in its network management. With power use climbing, many data centers are using free cooling to reduce their reliance on power-hungry chillers. By foregoing chillers entirely, Google will need to reroute workloads if the weather in Belgium gets too warm. The facility also has its own water treatment plant so it doesn't need to use potable water from a local utility."

132 comments

  1. Global warming by indre1 · · Score: 1, Troll

    Guess they'll be in big trouble when global warming strikes Belgium!

    1. Re:Global warming by Fenax · · Score: 1, Insightful

      Belgium is already too warm ! *here a Belgian complaining about weather*

    2. Re:Global warming by lewko · · Score: 2, Funny

      No. They will just sponsor Al Gore to speak about global warming at a local meeting. Thanks to the Gore Effect, the temperature usually drops dramatically as soon as Gore arrives.

      --
      Do you or your partner snore? - Visit www.snoring.com.au
    3. Re:Global warming by frosty_tsm · · Score: 3, Interesting

      I have to back this up. TFA says the maximum temperature in Brussels is 66 to 71 degrees. I recall it being warmer than that during the summer I lived there. I can't quite remember the temperature, but 24 or 25 C (which is in the mid to upper 70s F) comes to mind.

    4. Re:Global warming by mister_playboy · · Score: 2, Insightful

      Upper 70s??? I'd go for that. I've had about enough of this 100 degree BS here.

      --
      Do what thou wilt shall be the whole of the Law ::: Love is the law, love under will
    5. Re:Global warming by schon · · Score: 2, Funny

      Guess they'll be in big trouble when global warming strikes Belgium!

      Don't be silly. Everyone knows that Belgium doesn't really exist.

    6. Re:Global warming by jonadab · · Score: 2, Informative

      > Guess they'll be in big trouble when global warming strikes Belgium!

      If global warming ever did what the alarmists keep saying it's going to do, chillers would probably become completely irrelevant, since about two thirds of Belgium would be continuously surface-mounted with a very large water-cooling rig and heatsink, sometimes known as the North Sea.

      --
      Cut that out, or I will ship you to Norilsk in a box.
    7. Re:Global warming by goarilla · · Score: 1

      just wait 30 minutes !

    8. Re:Global warming by Anonymous Coward · · Score: 1, Interesting

      max temp in the center of Belgium ever recorded was 38ÂC (and that's like 50 years ago). a very hot summer is a summer with a 15 day period with max temps above 30Âc.

      (in the northern part of Belgium, you can get up to 40+ ÂC, but the Google datacenter is further down south.)

      ÂC = degrees celsius (seems like it's not getting through properly for whatever reason)

  2. What's next? by ickleberry · · Score: 5, Funny

    If it wasn't for the required internet connectivity google could go off the grid completely. But they already own so much fibre and the public internet seems to need google more than they need it.

    Soon they will generate all their own power from wind and solar, convert all their employees shit to power so they don't need the sewerage system either, send all their traffic through the network of low earth orbit satellites they are about to launch which also conveniently beam solar power back down to them.

    So basically at the end of the day they will be able to buy or swindle a plot of land from some country with low tax, bring in all their own employees, contribute absolutely nothing to the local economy and leave when the sun goes down. It's great really, saves them on lawyers that would otherwise help them pussyfoot through the swaths of modern over-regulation and the satellites will help them get past any censorship / connectivity problems.

    And if China start shooting down their satellites, Google will make satellites that shoot back

    1. Re:What's next? by Anonymous Coward · · Score: 5, Funny

      I am totally buying Google stock if they do this.

    2. Re:What's next? by Anonymous Coward · · Score: 1, Funny

      You can't generate power from Google employees shit; power generation requires stinky shit and their shit does not stink.

  3. Unreliable... by Darkness404 · · Score: 4, Interesting

    So basically everything gets rerouted on a hot day. Ok, that sounds fine until you realize that most of the outages of Google's products were due to, rerouting. And also, it seems odd that the cost of building a (hopefully redundant) datacenter that is this unreliable would be less than consolidating it with another one and using electrical cooling.

    --
    Taxation is legalized theft, no more, no less.
    1. Re:Unreliable... by martas · · Score: 5, Interesting

      well, it might be unreliable, but i think you're overestimating the reliability of normal data centers. even if failure is twice as likely at this data center than others, i think it still improves overall performance and reliability enough that it's worth building. or at least google seems to think so.

    2. Re:Unreliable... by Anonymous Coward · · Score: 1, Insightful

      Of course, if they have to do the re-routing 10 or so times a year, they will get the kinks worked out. That is far better management scheme than having a fail-over plan that never really gets tested. Also, when temps rise, they probably won't be completely off-lining this data center, just a fraction of the containers within it.

      I also wonder if they might not be fibbing a little, the air handlers come in different types. For chilled water use, they wouldn't have compressors, the chilled water is run through the heat exchanger. There are also air-handlers that use "process water" which is more like room temperature. These have built-in compressors with a freon (or whatever) loop. Freon goes though the heat exchanger and the process water is used to remove the heat. I'd bet this data center has some of this type of air handler and they would be effective even on hot days.

       

    3. Re:Unreliable... by j79zlr · · Score: 5, Informative

      If you have chilled water, you have a chiller, which means you have compressors. Process water or ground source water usually is not cold enough to be an effective cooling medium. You want a high delta T between the entering air temp and the entering water temp to induce heat transfer. Closed loop ground source water is extremely (prohibitively) expensive and open loop is quite a maintenance hassle due to water treatment. High efficiency chillers paired with evaporative cooled water towers with economizer capability is very efficient and reliable. Usually you can get down to around 0.5kW per ton with high efficiency chillers at full load and with multiple staged compressors you can do even better with part load conditions. The cooling towers are usually pretty low with around 0.05 to 0.15kW per ton. Use VFD's on the secondary pumps and cooling tower fans, and you can get cooling in at 0.75kW per ton for the whole plant at peak and even lower and part load conditions (95% of the time).

      I just designed a data center for a large Big Ten univeristy and there were no large air handlers involved at all. The system had two 400-ton chillers with the chilled water piped directly to rack mount APC fan coils. Without "green" being the basis of design, the chiller system still operates right at about 1kW/ton.

      --
      I'm not not licking toads.
    4. Re:Unreliable... by SlashV · · Score: 3, Funny

      So basically everything gets rerouted on a hot day.

      Exactly, and you can stop googling, get out of the basement and go to the beach. How bad is that ?

    5. Re:Unreliable... by slashqwerty · · Score: 2, Interesting

      It's mildly interesting to know how many KW of power it takes to move some water but it would be more interesting to know how many KW of power it takes to transfer heat. With your measurements, how much heat can you transfer with a ton of water and how does the temperature of the computers compare to the ambient air?

    6. Re:Unreliable... by Xiterion · · Score: 3, Informative

      A ton is a measure of the amount of heat transferred. See this for more details. It's also worth noting how much of the heat transfer is done by way of allowing the water in the system to evaporate.

    7. Re:Unreliable... by cynyr · · Score: 2, Informative

      the short answer is that the ton mentioned above in the HVAC industry is roughly equivlent to the amount of cooling a ton of ice (frozen water) would provide. Somedays I wish my industry would just unhitch the horse, and burn the buggy it was attached to.

      --
      All of the above was encrypted with a Quad ROT-13 method. Unauthorized decryption is in violation of the DMCA.
    8. Re:Unreliable... by j79zlr · · Score: 3, Interesting

      1 ton is a unit of cooling equal to 12,000 BTU/hr, not weight. The typical rule of thumb is 2.4 GPM per ton which is based on a standard 10degF delta T, usually 44degF to 54degF. Assuming 100 feet of head and 50% mechanical efficiency, 1 BHP will move about 20 gallons of water per minute. 1 BHP is about 0.75kW.

      I am kind of confused about how many kW of power it takes to transfer heat. Heat moves from high to low, you have to pump cold water through a coil and force warm air across that coil. The amount of heat transferred is a function of the face velocity and temperature of the air across that coil, the amount of fluid moved and temperature through the coil and the characteristics (fin spacing, fin size, material) of the coil.

      The temperature of the computers isn't really the important factor, it is the heat rejected. Again using rules of thumb, you can assume that 80% of the electrical power delivered to the computers will be dissipated as heat. The total of that heat rejected along with the other heat inputs to the space, e.g. lighting, walls, roof, window loads, etc., will determine your cooling load. Almost all of this load is sensible, meaning heat only, for other occupancy types you would also have to consider latent (moisture) loads as far as people and ventilation air in determining the amount of cooling needed.

      --
      I'm not not licking toads.
    9. Re:Unreliable... by jra · · Score: 1

      400 ton, and they did it with water, not glycol?

      Can you talk a little more about the decisions between those 2?

    10. Re:Unreliable... by jhw539 · · Score: 5, Interesting

      You do not need a chiller to operate a datacenter in many environments at all. Based on the 2nd edition of ASHRAE's Thermal Guidelines for Data Processing Environments (which was developed with direct input from the major server providers), you can run a datacenter at up to 90F. Seriously, 90F into the rack. When it comes out the back of the rack, you collect the heat exhaust at 100-110F. "Chilled" water at 81F is more than enough to knock that 110F down to 90F- ready to go back into the front of the rack.

      The 81F water can be produced directly from open cooling towers (direct evaporation) whenever the wetbulb is lower than 76F (4 degree approach plus a 1F on your flat plate that isolates the datacenter loop from the open tower loop).

      You designed an efficient datacenter, but you're five years behind cutting edge (not actually a bad thing for most critical environment clients). The next wave of datacenters will have PUEs of 1.2 or less and redefine the space from a noisy but cool space to hang out to a hot machine room with industrial heat exhaust design.

      I actually just finished a chiller less 8MW schematic design and analysis for a bid. It was my second this month (the first was a cake walk - an extreme Twb of 67F, the second was west coast light conditions).

      PS: Secondary pumps? Seriously? Unless you have to boost up to 25 psi to feed a Cray or some other HPC I thought everyone who cared had moved onto variable primary-only pumping. (Sorry, feeling a bit snarky after hitting a 40 hour week on Weds...)

    11. Re:Unreliable... by jhw539 · · Score: 3, Informative

      "Again using rules of thumb, you can assume that 80% of the electrical power delivered to the computers will be dissipated as heat."

      ? 100% of the electrical power delivered to the computer is dissipated as heat. It's the law. It will be far less than the nameplate power (that electrical uses), and perhaps 80% of what is delivered to the building (after transformer, UPS, and PDUs), but it all ends up as heat (unless you're splitting hairs about the acoustical energy emissions and velocity pressure in the exhaust, which is small and quickly converted to heat).

    12. Re:Unreliable... by j79zlr · · Score: 1

      I guess I was unclear, 80% of the circuit size(s) delivered to the units since you can't load a circuit to more than 80% of the breaker size.

      --
      I'm not not licking toads.
    13. Re:Unreliable... by j79zlr · · Score: 4, Informative

      The units were mounted on the roof, but were packaged AAON 2 x LL210 chillers (and a full 400 ton backup) with no exposed exterior piping. Glycol reduces the specific heat of the fluid and increases the specific gravity, so it can move less heat and takes more power to move. I only add glycol to the system if freezing is an issue.

      --
      I'm not not licking toads.
    14. Re:Unreliable... by j79zlr · · Score: 2, Informative

      Our design conditions were 75degF. The server manufacturers said they can handle up to 100degF but have much longer life with cooler room temps.

      Primary loop is feeding the chiller. Most chillers don't like variable flow. The secondary loop is feeding the load.

      --
      I'm not not licking toads.
    15. Re:Unreliable... by Glendale2x · · Score: 2, Insightful

      Servers may be able to operate at 90-100, but they simply won't last as long being cooked compared to equipment that lives at cooler temperatures. This probably doesn't matter if you're Google and don't care about burning hardware or if you have money to spare and are always installing new equipment, or would rather generate truckloads of electronics waste replacing servers faster than a cooler facility just to get a PUE to brag about. The rest of us will have to settle for server rooms with air conditioning for now.

      --
      this is my sig
    16. Re:Unreliable... by Glendale2x · · Score: 1

      Or, if you're Google, you have a metric shit-ton of servers and don't care too much about reducing the MTBF of a few hundred racks by running them hot.

      --
      this is my sig
    17. Re:Unreliable... by Anonymous Coward · · Score: 0

      It's highly doubtful that 80% of the circuit amps are being used. (The power factor might be about 0.8, giving you watts equivalent to 80% of volt*amps)
      The electrical connected load is much less than the average electrical usage, usually around 40%. In most circumstances, assuming 50% to 60% of nameplate wattages are converted to heat would be a reasonable guesstimate for cooling purposes.
      Cooling equipment will only see the average heat output, whereas the nameplate wattages are typically much higher due to short-lived greater currents.

    18. Re:Unreliable... by russotto · · Score: 1

      Or, if you're Google, you have a metric shit-ton of servers and don't care too much about reducing the MTBF of a few hundred racks by running them hot.

      I was under the impression (mostly from tons of slashdot articles on the subject), that Google had done the research on this and determined that the higher temperatures did NOT reduce the MTBF of the hardware. Seriously, 90F into the equipment isn't that hot.

    19. Re:Unreliable... by Critical+Facilities · · Score: 1

      If you have chilled water, you have a chiller, which means you have compressors

      While I agree with you on that point, I think what the GP was saying is that it is indeed possible that the CRAC units being used at Google's "Chiller-less" Data Center could very well have compressors contained in them, along with condenser barrels.

      You'll notice TFA does not specifically say that there is no mechanical cooling happening at this site, only that their focus is on free cooling. It could very well be that these CRACs have the ability to modulate between mechanical cooling and water side economizer cycle using a water coil. It would be interesting to find out if this were the case.

    20. Re:Unreliable... by jhw539 · · Score: 2, Informative

      "Servers may be able to operate at 90-100, but they simply won't last as long being cooked compared to equipment that lives at cooler temperatures."

      Operating 500 hours a year at 90F (the peak of the allowable range) is unlikely to impact longevity. 100F is outside of the allowable range. Your opinion is contradicted by what IBM, Intel, Dell, Sun, and numerous datacenter owners along with the design professionals at ASHRAE have developed over the course of several years of research and many (mostly dull) hours of debate.

      There are special cases, tape machines are glaring examples, but operating a datacenter at 80-90F does not have any correlation beyond old wive's tails with increased equipment failure. Indeed, such a 10F difference in actual component temperature (which is what matters) can occur merely between different manufacturer's case layout or the use of meshed back security rack.

    21. Re:Unreliable... by Glendale2x · · Score: 1

      The only actual experience I have that contradicts your opinion is a UPS shorting its inverter and static bypass after two years of being in an 80-90 degree room during the summer, giving it a peak internal temp of 110.

      --
      this is my sig
    22. Re:Unreliable... by DragonWriter · · Score: 1

      So basically everything gets rerouted on a hot day.

      Except that its not "everything", even on a hot day, its just that the total load at that center must be reduced (not eliminated) on a hot day.

      And also, it seems odd that the cost of building a (hopefully redundant) datacenter that is this unreliable would be less than consolidating it with another one and using electrical cooling.

      Google needs to have many data centers, and problems it has had in the past have shown that it needs to have the ability to seemlessly shift load between them anyway; so, for them, this is just another factor in the determination of where load should be shifted. It may not be more cost effective for other companies, whose baseline data center needs are different.

    23. Re:Unreliable... by NotBornYesterday · · Score: 1

      I've got one word for you: Iceland.

      They sit where temperate ocean water meets cold arctic air, resulting in a relatively narrow and predictable temperature band which happens to be perfect for cooling datacenters with minimal, if any, conventional HVAC. Their power is green, and they have lots of it. They use a combination of hydropower and incredibly abundant geothermal heat for power generation. Recently, undersea fiber cables have been laid down, greatly increasing their connectivity to the outside world. Not to mention that these days, the cost of doing business there is fairly attractive.

      I suppose that a detractor could observe that Iceland is a geologically active area, but then again so is Silicon Valley.

      If Google had some real foresight, they'd be investing in an Icelandic datacenter right now.

      --
      I prefer rogues to imbeciles because they sometimes take a rest.
    24. Re:Unreliable... by jhw539 · · Score: 1

      Correlation doesn't equal causation. I've seen more failures in 70F UPS rooms... Some equipment did have trouble with high temps, but all new equipment can and should be able to take 80F normal operating temperature with limited excursions up to 85-90F. And the more common correlation is claims of higher failure rate for servers at the top of a rack. In most traditional datacenters, you can find hotspots where recirculation from behind results in a continuous 80+F temperature into the server. When we talk about running a datacenter at 80F, you CANNOT have hot spots - you must have solid partions between hot exhaust and cold aisle intake. This is a key issue. Most datacenters with a 70F setpoint actually need it to maintain 80F intake at the ends of rows or tops of racks in areas with messed up airflow management.

  4. Urine by Anonymous Coward · · Score: 0

    Why not go the extra mile and use recycled urine?

  5. Worth the tradeoff? by Clockowl · · Score: 4, Interesting

    Is it really worth to be dependent on the weather in exchange for a lower energy bill?

    1. Re:Worth the tradeoff? by symbolset · · Score: 4, Insightful

      If you're Google? Apparently the answer is "yes."

      More people can and should do this. 27C is plenty cool enough for servers. It annoys me to go into a nipple crinkling datacenter knowing they're burning more juice cooling the darned thing than they are crunching the numbers. A simple exhaust fan and some air filters would be fine almost all of the time, and would be less prone to failure.

      --
      Help stamp out iliturcy.
    2. Re:Worth the tradeoff? by Anonymous Coward · · Score: 0

      Um, Yes?

    3. Re:Worth the tradeoff? by Junta · · Score: 2, Interesting

      It's probably not as much about the energy bill as it is about the PR.

      If it wasn't PR, they'd have chillers 'just in case', even if turned off most of the time. As it stands, they may be subject to a large risk of month-long heat waves killing them on paying idle employees, taxes, and taking a hit on capital depreciation costs for zero productive output that they are presumably banking on by bothering to build another datacenter.

      Of course, there may be something unique about the site/strategy that makes this threat near zero that I'm unaware of, but I've seen facilities that are largely cooled by climate pretty far north that still keep chillers on hand in the event of uncooperative weather.

      --
      XML is like violence. If it doesn't solve the problem, use more.
    4. Re:Worth the tradeoff? by BobisOnlyBob · · Score: 1

      I've seen facilities that are largely cooled by climate pretty far north that still keep chillers on hand in the event of uncooperative weather.

      Very true, but this is Google we're talking about; their re-routing ability is phenomenal thanks to the sheer number of data centres they have across Europe. The latency cost for a re-route away from Belgium to North France or North Germany on a hot day is minor, most companies wouldn't have so many similar data centres proximal to the one shut down by inclement weather - it's a risk that will more than pay off. Besides, everyone gets lethargic on hot days - it seems Google now does too!

    5. Re:Worth the tradeoff? by mckinnsb · · Score: 2, Interesting

      Yes , but not because of the bill itself.

      Google has been actively developing a reputation in the corporate world for squeezing the most CPU-bang out of a buck, and a great way to do that is by cutting down on the amount of power a CPU uses.

      A few weeks back there was an article on Slashdot which discussed a before-unseen Google innovation concerning its servers - a 12 volt battery that cut the need for an APC (which lowered costs by lowering both the power flowing to the CPU and the power required to cool the APC).

      Google is trying to cut power out of the equation here as well, but with a different spin. Google is attempting to see if it can design a data center that does not require a cooling system that can perform satisfyingly within operating temperature range in a temperate climate - without any direct physical intervention (except by software algorithms). The implications are huge.

    6. Re:Worth the tradeoff? by Anonymous Coward · · Score: 0

      A check of one weather site indicated that the maximum recorded temperature it had for Brussels was 96 F. Most server equipment is happy with a true ambient temperature of 90. That may put the exhaust temperature at 110 or so. With a single pass system (venting the exhaust directly outdoors, and bringing in new air from outside) an external temperature of 90 could work. Since the average high temperature in Brussels is apparently 71, only in pretty severe heat waves where temperatures exceed 90 would a data center need to shut down.

      At cooler temperatures more traditional systems could be utilized to manage internal external heat exchange.

  6. Reroute the weather instead by basementman · · Score: 4, Funny

    Why not just reroute the weather? Once google gets into cloud seeding and all that they really will be SkyNet.

    1. Re:Reroute the weather instead by ickleberry · · Score: 2, Funny

      They've done cloud computing, so cloud seeding should be a piece of cake

    2. Re:Reroute the weather instead by fuzzyfuzzyfungus · · Score: 1

      That would fit with their new "stomping on Microsoft's toes" strategy...

    3. Re:Reroute the weather instead by e9th · · Score: 3, Funny

      Bill Gates is already working on that. Google could send hurricanes his way, and Bill could try to kill them.

    4. Re:Reroute the weather instead by Heytunk · · Score: 1

      Google search built ontop of bittorrent!

      Where your search is dynamically routed to the nearest seed in the cloud.
      Please remember to seed after downloading your search results damn leachers.

    5. Re:Reroute the weather instead by Anonymous Coward · · Score: 0
  7. Running on the dark side of the planet by Anonymous Coward · · Score: 1, Interesting

    I wonder if it would be feasible to have massive passive cooling (heat sinks, fans, exhausts from the data center, etc.) and run the data centers which are currently at night (i.e. on the dark side of the planet.) and constantly rotate the workload around the planet, to keep the hotest centers in the coolest part of the planet. The same logic could be applied moving workloads between the northern and southern hemispheres.

    Yes, there would be tons more telecommunication to do, with the impacts on performance, data transmission costs and extra heat required to run all those routers at 120%, but there are fewer routers than servers, no?

    1. Re:Running on the dark side of the planet by maharb · · Score: 1

      Except that the highest load on data centers is generally during the local day or at least not at like 5am when its the coldest. I would imagine routing the traffic all the way to the dark side of the planet would produce less than acceptable latency for most uses. This might work for other types of work but I don't think it would work for anything web and response time based like google.

      Plus routers/bandwidth isn't exactly cheap and costs would go up if companies started using these methods. I'm not going to say I did a cost analysis but I don't think this would add up to a savings. All the saving you would have gained in reduced energy costs would go right back to routers, bandwidth, and all the other insane costs that would be needed to maintain and build out this plan.

      Why go through all of this when you could just build a datacenter closer to the poles where it is always cold day, night, summer, and winter. The routes would be faster, it could stay online all the time, and it follows the same models we currently use so it's is way more likely to be successful.

    2. Re:Running on the dark side of the planet by denzacar · · Score: 1

      1 - You are thinking too small and apparently you are falling for the idea that Google is "just a search engine". It's OK. Many people do that.
      It is not all "web", nor do they have to use all their power for themselves.

      The idea is to offer "virtualized workloads" to your customers - workloads that you then shift around the world to the "cheapest work-area at the moment"
      Which MIGHT cost you a pretty penny - unless you have your own global network of datacenters built for just such a purpose.
      You know... something a company like Google just might have.

      2 - You are thinking too big.
      You don't need to go to the "dark side" (of the planet). Just shift your workloads couple of hours to the east-northeast.
      In most cases they would not be chasing night-time - just those couple of hours of off-peek electricity during the dawn (read: cheaper) and possibly colder servers.
      It is actually mentioned in TFA. RTFA it.

      As for placing datacenters beyond the arctic circle - my guess is that they are going to keep building their datacenters closer to the for some time to come.

      --
      Mit der Dummheit kämpfen Götter selbst vergebens
    3. Re:Running on the dark side of the planet by maharb · · Score: 1

      Did you read the post I replied to. Obviously not. This was not talking about reducing cooling costs by using non peak electricity. It was talking about using passive cooling. Passive cooling must be done at the coldest times of the day which is exactly when there are the lest users of ANY application that involves people actively using the system not just www web.

      My first post was NOT a reply to the article, it was a reply to someone advocating passive cooling by rerouting traffic based on the cold parts of the day. I countered with why not use the cold parts of the world for passive cooling.

      You are advocating something completely different which I do not wish to disagree with.

      So before you go off telling me to RTFA why don't you RTFParent I replied to. Thanks.

  8. Investing by corychristison · · Score: 2, Funny

    I think Google needs to start investing some time and money into buying or building Nuclear Power Facilities.

    It could pay off for them, because they certainly don't need all of the power they would generate, and could sell some back to the Country/State/Region they build it in.

    Sounds like a win-win to me.

    P.S. - Please don't start a flame war about how Nuclear Power is 'unclean' or 'dangerous' -- in today's society it is cleaner, more efficient and just as safe, if not safer, than coal-fired generators.

    1. Re:Investing by Anonymous Coward · · Score: 0

      how about unsustainable? Yellow cake is not that prolific in the earths crust. Even using breeding techniques and having India and CHina be players in the Nukes game we will run out of Uranium fast.

    2. Re:Investing by PJ6 · · Score: 1

      Nuclear reactors have lead times of 10 years or more, and you are proposing this for an internet-based business. Reactors are also insanely expensive and carry enormous political problems. Um, yeah... like, that's totally going to work.

    3. Re:Investing by Anonymous Coward · · Score: 0

      Belgium has nuclear power. I'm not sure what proportion of their power nuclear supplies, but their neighbour France gets 80% from nuclear. The Belgians, along with most of the world, also have a legal system that is much saner than that of the USA, so the lead times are not likely to be anything like as long. The Belgian autoroute system is mostly lit at night, apart from some bits in the Ardennes, so I suspect that power there must be relatively cheap.

    4. Re:Investing by Homburg · · Score: 1

      A nuclear power station does make sense as an investment for Google; after all, they've got plenty of experience of investing in things that are never going to make a profit.

    5. Re:Investing by BeaverCleaver · · Score: 1

      Maybe this sort of initiative is just what is needed to renew public interest in nuclear power. If a business like Google can show that it is clean, safe and reliable, perhaps governments and "environmentalists" can see through the FUD and support nuclear for national grid power.

    6. Re:Investing by Foolicious · · Score: 1

      Mmm...yellow cake...with radioactive frosting...

      --
      Please don't use "umm" or "err" or "erm".
  9. It's belgium by Anonymous Coward · · Score: 0

    "The climate in Belgium will support free cooling almost year-round, according to Google engineers, with temperatures rising above the acceptable range for free cooling about seven days per year on average. The maximum temperature in Brussels during summer reaches 66 to 71 degrees, while Google maintains its data centers at temperatures above 80 degrees."

    yep. it's never too hot in belgium. it's because the sun never shine here. Sky is always full of grey clouds and It's almost always raining. but hey... that's my country!

    1. Re:It's belgium by schon · · Score: 1

      The maximum temperature in Brussels during summer reaches 66 to 71 degrees,

      Holy crap! And I thought it got hot around here when it hit 39 last year! I always thought Belgium was in northern Europe.. 66 degrees sounds more like the tropics to me!

    2. Re:It's belgium by Anonymous Coward · · Score: 0

      Fahrenheit or Celsius? I am sure 71 degress is in Fahrenheit but I don't know anyone who would truthfully say 39 Fahrenheit is hot. And I use to live in Northern Alberta.

    3. Re:It's belgium by schon · · Score: 1

      Fahrenheit or Celsius?

      Well, being as only a couple of backwater countries still use Fahrenheit, and Belgium isn't one of them, that must mean that temperatures discussed are in Celsius.

  10. Great Opportunity for New Zealand by nokiator · · Score: 1

    As the number of chiller-less data centers in the Northern Hemisphere increases, New Zealand may become the ideal location to build alternate climate data center capacity to deal with hot summers in Europe and Northern America... :)

    1. Re:Great Opportunity for New Zealand by destroyer661 · · Score: 1

      Only problem is getting enough bandwidth to/from New Zealand to make the data center worth it. It's one thing to build one there and have it be super efficient and climate effective, but it's another to have all that greatness and not be able to get enough information to/from it.

      This picture only shows 1 cable from NZ to NA, and none to Europe, so I'd say it's out of the picture.

      --
      #define true false // Have fun debugging!
    2. Re:Great Opportunity for New Zealand by mdf356 · · Score: 1

      Not all of North America is hot in the summer...

      Average high in SFO for July-September is 72
      Average high in SEA for July-Aug is 76

      Lots of places on the west coast rarely get warm. This is one reason everyone and their kid brother has moved there, which is why real estate is so expensive...

      --
      Terrorist, bomb, al Qaeda, nuclear, yellowcake, kill, assassinate. Carnivore is dead... long live Echelon.
  11. Re:Unreliable...Probably not by Banzai042 · · Score: 5, Insightful

    Remember that even on hot days not all of the traffic through the datacenter needs to be rerouted, and I'd imagine that a location selected for a datacenter like this was chosen for the infrequency of days that will require rerouting. Do you know how much it costs to cool a datacenter, and how much this will save? I don't, but Google probably does, and they probably wouldn't make a decision to do something like this without comparing the savings with the potential cost from decreased lifespan of computers running hot and losses due to downtime. I would also imagine that Google will be working to greatly increase stability during rerouting, given the comments from the end of TFA about other power saving uses, such as routing traffic to datacenters where it's night, meaning "free cooling" can be used since it's colder outside, and off-peak electricity rates are in effect.

    I think the concept is interesting, and it makes me wonder if we'll see more datacenters built in areas of the world more conducive to projects like this in the future.

  12. This might be a dumb question by HangingChad · · Score: 2, Interesting

    But if your data center is in say, Minnesota, it seems like you could balance the temperature with outside air for many months out of the year. Obviously you'd need to light up the chillers in the summer, but running them 4 months out of the year seems like a huge energy savings than running them year round.

    I remember visting Superior in the summer and the lake water was freezing f'ing cold even in June. Wonder if you could run a closed loop heat exchanger without screwing up the lake environment?

    --
    That's our life, the big wheel of shit. - The Fat Man, Blue Tango Salvage
    1. Re:This might be a dumb question by LoRdTAW · · Score: 3, Informative

      I don't know about natural lakes but man made ponds have been used for just that purpose.

    2. Re:This might be a dumb question by Five+Bucks! · · Score: 3, Informative

      They do! Well... not Superior, but Lake Ontario.

      Toronto has a rather large system that uses deep, cool water as a heat sink.

      Enwave is the company that provides this service.

      --
      52 52'23" W 47 32'07" N
    3. Re:This might be a dumb question by maxume · · Score: 1

      The rough answer is yes you can, but there are probably questions about how much you are willing to screw up the environment and whether or not you can get licensed:

      http://en.wikipedia.org/wiki/Presque_Isle_Power_Plant

      (I'm not asserting anything about how much heat the Presque Isle Plant releases into Lake Superior or about how much damage that heat does, but it probably releases a significant amount of heat, and it probably has some sort of license)

      --
      Nerd rage is the funniest rage.
    4. Re:This might be a dumb question by david.given · · Score: 4, Interesting

      The short answer is yes --- water takes a staggering amount of energy to change temperature (it's one of the many properties the stuff's got that's really weird). A big lake makes an ideal dumping ground for waste heat. What's more, the environmental impact is going to be minimal: even the biggest data centre isn't going to produce enough waste energy to have much effect.

      (A big data center consumes about 5MW of power. The specific heat capacity of water is about 4kJ/kg.K, which means that it takes 4kJ to raise the temperature on one kilogram of water by one kelvin. Assuming all that gets dumped into the lake as heat, that means you're raising the temperature of about 1000 litres per second by one kelvin. A small lake, say 1km x 1km x 10m, contains 10000000000 litres! So you're going to need to run your data centre for ten million seconds, or about 110 days, to raise the temperature by one measly degree. And that's ignoring the cooling off the surface, which would vastly overpower any amount of heat you could put into it.)

      (The same applies in reverse. You can extract practically unlimited amounts of heat from water. Got running water in your property? Go look into heat pumps.)

      In fact, if you were dumping waste heat into a lake, it would make sense to try and concentrate the heat to produce hotspots. You would then use this for things like fish farming. Warm water's always useful.

    5. Re:This might be a dumb question by TubeSteak · · Score: 3, Interesting

      I don't know about natural lakes but man made ponds have been used for just that purpose.

      Man made ponds are used because the EPA crawls up your ass if you want to use a natural body of water for any commercial/industrial output.

      Note: I'm saying that's a bad thing. I'm glad the "good old days," when chemicals, raw sewage, and cooling water were dumped willy nilly into the waterways and drinking supply, are gone. You warm up an area of water 10 or 15 degrees farenheit and you'll kill most everything living in it but algae.

      --
      [Fuck Beta]
      o0t!
    6. Re:This might be a dumb question by bill_mcgonigle · · Score: 1

      The rough answer is yes you can, but there are probably questions about how much you are willing to screw up the environment and whether or not you can get licensed:

      In high school we went down to the Oyster Creek nuclear power plant a few times for class trips. They have a cooling water drain to a creek that eventually feeds into an estuary. In the winter, the area is teeming with wildlife that love it. There are clam beds unlike any area around it. They've actually created fish kills by turning off the plant in winter (and on occasion have cooked a few as well since so many fish congregate).

      I hear some people have built homes near there and put in docks because you have a free heated pool year-round. Why they can't further extract useful energy from this hot water I don't know.

      --
      My God, it's Full of Source!
      OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
    7. Re:This might be a dumb question by jhw539 · · Score: 2, Interesting

      "Why they can't further extract useful energy from this hot water I don't know."

      I blame that bastard Carnot personally for this... They could get additional work out of that hot water, but it gets prohibitively expensive the lower your delta T between hot and cold gets. I was all stoked about finding some sort of stirling heat engine to run off some datacenter waste heat, until I worked the numbers and found the annual average maximum therorectical efficiency was under 15%.

      F*cking entropy.

    8. Re:This might be a dumb question by CAIMLAS · · Score: 3, Interesting

      At those latitudes the ambient subterranean temperature remains pretty ambient all year long. Drill into the side of a mountain or hill with a boring tool, leave the edges rough (with a smooth poured/paved floor for access) and just drop your server containers in there with power coming in. If you go all the way through the hill you can use the natural air currents to push/pull air through the tunnels, and the natural heat absorption qualities of stone will keep the temperature down. I'd be surprised if any active "cooling" were needed at all.

      --
      ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
    9. Re:This might be a dumb question by Anonymous Coward · · Score: 0

      water takes a staggering amount of energy to change temperature

      It takes 1 btu to raise 1 lb of water 1 degree F. That's not a staggering amount of energy. Put another way, a 1 Ton window A/C unit removes enough heat to turn 2,000 lbs of water into ice every day.

    10. Re:This might be a dumb question by dlevitan · · Score: 3, Informative

      Cornell University actually did this exact thing to cool a good chunk of the campus. It's called lake source cooling. While there will of course be some environmental impact, the energy usage is 20% of normal chillers and thus is, I'm sure, an environmental net gain.

    11. Re:This might be a dumb question by Anonymous Coward · · Score: 0

      We were looking at using Lake water for a Beowulf cluster at the University of Toronto. I can't really go into the details but it involved evaporation cooling of the processors using a special liquid and cool water to recondense the liquid. The warm water would then be pumped through a radiator to cool it off before introducing it back into the Lake.

    12. Re:This might be a dumb question by mydots · · Score: 1

      Geothermal heat transfer is a great way to do cooling (and heating if needed). The initial investment will be high, but the savings will also be high in the long run (and not just in $). Add solar panels and/or wind turbines that can power the heat pump and some of the data center equipment. I had a solar system installed on the roof of my house a few years ago. I received major incentive rebates from the state, I can sell my SREC's and I get "free" electricity; and in a few more years time the cost of the system will have paid for itself. It has been a good investment. I researched geothermal for the house earlier this year and plan to invest in that within in the next few years. I have already reduced my carbon footprint by more than 30% in the last few years and plan to reduce it further. Just think how much more they could be reducing their carbon footprint.

    13. Re:This might be a dumb question by funkboy · · Score: 1

      Drill into the side of a mountain or hill with a boring tool, leave the edges rough (with a smooth poured/paved floor for access) and just drop your server containers in there with power coming in.

      Perhaps you were not aware that Belgium is flat as a crepe? Now, if they wanted to power the datacenter off the methane from the abundantly available cow and sheep poo, that would be something...

    14. Re:This might be a dumb question by CAIMLAS · · Score: 1

      I wasn't aware of that; interesting.

      The technique I described wouldn't need to be done in Belgium, though. I'm sure any one of the Nordic states would be well suited for it.

      --
      ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
    15. Re:This might be a dumb question by afidel · · Score: 1

      Well, the Great Lakes are basically barren down in the deepest zones so that's one heck of a heatsink. I know someone was talking about using the water coming into Chicago as a heatsink for free cooling as the water is too cold to be usable immediately anyways (like 56F I think).

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    16. Re:This might be a dumb question by bill_mcgonigle · · Score: 1

      "Just too expensive" makes perfect sense. I think their dump limit is at 97 degrees F.

      Thanks for the reply.

      --
      My God, it's Full of Source!
      OUTSIDE_IP=$(dig +short my.ip @outsideip.net)
  13. Yakhchal by physicsphairy · · Score: 4, Informative

    The ancient Persians had a passively cooled refrigerator called the yakhchal which "often contained a system of windcatchers that could easily bring temperatures inside the space down to frigid levels in summer days."

    Perhaps the Google datacenter could employ some variation of their technique.

    1. Re:Yakhchal by camperdave · · Score: 1

      "often contained a system of windcatchers that could easily bring temperatures inside the space down to frigid levels in summer days."

      Sounds like something out of Dune.

      --
      When our name is on the back of your car, we're behind you all the way!
    2. Re:Yakhchal by CAIMLAS · · Score: 2, Interesting

      This reminds me of a technique for cooling water in a desert which could tenably be applied to the data center as well.

      Basically, a container is filled with water, closed/sealed, and wrapped with a damp/wet towel and buried in the ground (or just placed somewhere in the sun, I suppose). The evaporation of the moisture in the rag will draw the heat from the inside of the container, resulting in frigid water.

      Put a data center on a dry coastal equatorial area and harness solar to desalinate the water. Build the data center under ground, with the roof of the center allowing easy flow of heat upwards, and then plant edible vegetation on top of the roof. Water the roof consistently to cool your data center during the day (and harvest the proceeds to sell/consume).

      It may or may not be worth it financially, but it'd probably work.

      --
      ~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
    3. Re:Yakhchal by Bruce+Perens · · Score: 3, Interesting
      You need both windcatchers and an underground water reservoir (a quanat). The windcatchers create a lower pressure zone which pulls air in through the quanat. There is evaporative cooling in the quanat. I don't think this would get near freezing temperature unless your water source is really cold.

      There is a way to make ice in a dry environment by exposing water to the coolness of the night sky and insulating it during the day.

    4. Re:Yakhchal by Anonymous Coward · · Score: 0

      I'm pretty sure they've already Googled that alternative.

  14. More interesting than we think... by History's+Coming+To · · Score: 3, Interesting

    So the fundamental upshot is that the point to point speed of the internet will be directly correlated to the average temperature of various cells, on a large scale. The statistical effect will be there. I'd wager this will be a remarkably accurate and near real-time barometer of global temperature.

    --
    Please consider this account deleted, I just can't be bothered with the spam anymore.
  15. Good to see. by Sir+Hossfly · · Score: 3, Interesting

    It's good to read some good news for a change...but it wont hit too many headlines..."Giant Googlebillion-dollar Company Doing Something Good" This "good" I speak of is someone with means and vision getting out there and just doing something. I still think Google could easily turn to the darkside...but is a whole different post ;)

  16. orly? by Anonymous Coward · · Score: 0

    COOL!

  17. Energy tradeoff of treating own water by SpaFF · · Score: 2, Interesting

    I'm not sure I understand why they constructed their own water treatment plant. I would think that it would be more energy efficient on the whole to use the already constructed municipal system in the area.

    --
    -----BEGIN GEEK CODE BLOCK----- Version: 3.12 GIT d? s: a-- C++++ UL++++ P++ L+++ E- W++ N o-- K- w--- O- M+ V PS+ P
    1. Re:Energy tradeoff of treating own water by seifried · · Score: 2, Informative

      You know what water costs in bulk? It adds up pretty quick. Plus they don't need potable (drinkable) water, they need water that won't clog their system up.

    2. Re:Energy tradeoff of treating own water by Runaway1956 · · Score: 2, Informative

      Municipal water (at least here, in the US) means "chlorinated water". Chlorine does terrible things to pipes, coolers, pumps - everything. Having your own water treatment system means the chlorine never gets in, saving bundles in maintenance. To get an idea, find two similar water cooled vehicles - one which has had chlorinated water added to the radiator routinely, and another whose owner has been more choosy. Look down into those radiators. I've actually seen copper radiators corroded out in states that use salt on their roads. (for the sake of argument, read "sodium CHLORIDE" although other salts are used on the roads)

      While chlorine would be the primary reason not to use municipal water, there are other contaminants in their water supplies as well. No boiler technician would willingly use city water, with or without chlorine, in his boiler if he can avoid it. Navy boilers run on distilled water, with desired preservative chemicals added, which translates into very long service lives.

      --
      "Windows is like the faint smell of piss in a subway: it's there, and there's nothing you can do about it." - Charlie Br
    3. Re:Energy tradeoff of treating own water by dbIII · · Score: 1

      They want water treated to work well with their cooling equipment and not just water good enough to drink. For instance where I am there are a lot of manganese salts in the drinking water that are perfectly safe to drink but tend to stick to hot surfaces. Using this water you would eventually clog up the pipes of a cooling system with the same brown gunk you get as a thin layer on the inside of electric kettles. There is other stuff that can precipitate out at different temperatures and basicly leave you with dirt in the pipes. Also a popular way to treat water to kill bacteria is to add a lot of oxygen to the water (bubblers etc), and while this does nothing to people the extra dissolved oxygen is corrosive to metals over long periods of time.
      In contrast the sort of treatment you want for cooling water can involve things like adding hydrazine to ensure there is very little dissolved oxygen which makes the water better for cooling but poisonous to drink. Then there can be the deliberate introduction of other poisionous material to kill diatoms and algae so they don't clog up the pipes.

    4. Re:Energy tradeoff of treating own water by Bill,+Shooter+of+Bul · · Score: 1

      Usually Chlorine, but you can also use bromine . Don't know if that would be any easier on pipes/pumps.

      --
      Well.. maybe. Or Maybe not. But Definitely not sort of.
  18. Comment removed by account_deleted · · Score: 1

    Comment removed based on user account deletion

  19. No chillers in Belgium by Anonymous Coward · · Score: 0

    Did anyone else think of weed when reading "chiller-less" and "Belgium"?

    1. Re:No chillers in Belgium by Anonymous Coward · · Score: 1, Insightful

      Did anyone else think of weed when reading "chiller-less" and "Belgium"?

      That's Netherlands.

  20. Why chillers at all, anywhere? by Anonymous Coward · · Score: 0

    At two meters below grade the soil is a constant 50F/10C or so.

    http://en.wikipedia.org/wiki/Geothermal_heat_pump, etc.

    As others have noted, that's plenty cool enough for most data centers.

    1. Re:Why chillers at all, anywhere? by fishbowl · · Score: 1

      >At two meters below grade the soil is a constant 50F/10C or so.

      Unless you introduce a heat source, and then it's extremely difficult to lose that heat since you're in such a well-insulated environment.
      Similar problems exist in cooling spacecraft. Sure it's "cold" in space, but if you have a local heat source that you want to shed, where do you send it and how?

      --
      -fb Everything not expressly forbidden is now mandatory.
    2. Re:Why chillers at all, anywhere? by Anonymous Coward · · Score: 0

      > Where do you send it, and how?

      I suggest you read the wikipedia article in the link.

      Pretty simple really.

  21. Buy 'land' in Greenland by Anonymous Coward · · Score: 0

    Buy land in Greenland - now!

  22. Re:Unreliable...Probably not by jhw539 · · Score: 1

    "I think the concept is interesting, and it makes me wonder if we'll see more datacenters built in areas of the world more conducive to projects like this in the future."

    Already happening in a way. Check out EDS's Wynyard facility. They didn't eliminate the chillers entirely last I looked, but in that climate they could have if they trusted the outdoor conditions and local code officials (open cooling towers are subject to abrupt shutdown if there is a Legionella scare anywhere near by in Europe).

    Although the lure of unutilized MW is a bigger pull. It's always nice to site a datacenter where the local utility overbuilt and isn't going to ream you when you ask for a MW or twenty.

  23. Re:Unreliable...Probably not by j79zlr · · Score: 4, Interesting

    That is where the ice storage systems become interesting and cost effective. In the states, usually half of a commercial energy bill is peak demand. If you can transfer that energy usage to night time to build up your ice storage and transfer your main power draw to off peak the savings can be very significant and create payback times in months not years.

    --
    I'm not not licking toads.
  24. Alaska! by postmortem · · Score: 0, Troll

    They could have used Alaska or N. Dakota instead and keep jobs in USA...

  25. Err... by samcan · · Score: 1

    Why didn't they just build it in Maine?

    1. Re:Err... by Jarnin · · Score: 1

      Better yet, why didn't they build it underground? I saw an episode of Dirty Jobs where they were digging tunnels to store wine barrels somewhere in California. They built these tunnels right under their fields, and once they were dug out they sprayed the walls with cement for structural support. Seemed like a great use of space to me.
      In a lot of places if you're down 5-10 meters you're looking at year-round temperatures of 10-13 Celsius (50-55 F). If you're underground, you've got usable land above you for things like agriculture and/or wind or solar power.

      This seems like a no-brainer to me...

    2. Re:Err... by Fzz · · Score: 1

      Basically the underground temperature will roughly be the mean year-round overground temperature, so long as you're not in a geothermally active area. That's where your 10-13C number comes from. But that only applies if you don't inject more heat than the ground can conduct away. The year-round mean temperature in London is probably around 10C. But the temperature in the London Underground in mid summer on the deep lines is more like 30C. Too much heat generated by the trains and people for the rock/clay to conduct away. A data centre generates for more heat in a small space than an underground railway does.

  26. Iceland by Skapare · · Score: 1

    Lots of cool weather and lots of cheap geo-thermal power.

    --
    now we need to go OSS in diesel cars
  27. Just being lobby-savvy... by PensivePeter · · Score: 3, Interesting

    I wonder how much this is a cynical marketing and public policy exercise. A few months ago, the European Commission announced an ambitous programme to the IT industry for European energy conservation targets to be met by 2012 and lo and behold, look who's here preening its feathers?

  28. The worst part of global warming has been the cold by Futurepower(R) · · Score: 1

    The worst part of global warming, for me personally, has been the unusual cold. I was living in Brazil during the summer that already finished there, and we didn't have a normal warm summer.

    Last winter in the U.S. here, it was so cold and icy it was not safe to go downtown for several days.

  29. Better solution by Nephrite · · Score: 1

    Move datacenters to Antarctica.

  30. RTFA - Google already thought of that... by denzacar · · Score: 1

    An Enabler for "Follow the Moon"?
    The ability to seamlessly shift workloads between data centers also creates intriguing long-term energy management possibilities, including a "follow the moon" strategy which takes advantage of lower costs for power and cooling during overnight hours. In this scenario, virtualized workloads are shifted across data centers in different time zones to capture savings from off-peak utility rates.

    This approach has been discussed by cloud technologists Geva Perry and James Urquhart as a strategy for cloud computing providers with global data networks, who could offer a "follow-the-moon" service to enterprise customers who would normally build data centers where power is cheap. But this approach could also produce energy savings for a single company with a global network - someone like Google.

    --
    Mit der Dummheit kämpfen Götter selbst vergebens
    1. Re:RTFA - Google already thought of that... by Richy_T · · Score: 1

      Clearly not astronomers.

  31. Correction... by denzacar · · Score: 1

    UPS! Lost a couple of words there, putting that link in.
    That last sentence should read:

    As for placing datacenters beyond the arctic circle - my guess is that they are going to keep building their datacenters closer to the internet backbones for some time to come.

    --
    Mit der Dummheit kämpfen Götter selbst vergebens
  32. marlor by cryptosense · · Score: 1

    Why Belgium? Taxes are high (I think highest in Europe) and in summer it can get to +-30C. Why not a country more to the north of Europe where it is cooler and with less tax?

    1. Re:marlor by afidel · · Score: 1

      Latency, bandwidth, and infrastructure (power surplus).

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  33. Anonymous Coward by Anonymous Coward · · Score: 0

    Why not just build them in the Arctic?

  34. Re:Cloud computing by jbatista · · Score: 1

    Or they can use Cloud Computing to predict cloud motion and therefore how to distribute work loads.

    --
    My sig is better than your sig.
  35. Google will need to reroute workloads by Anonymous Coward · · Score: 0

    Google will need to reroute workloads if the weather in Belgium gets too warm.

    Ha ha ha ha oh ho ho ha ha. Seriously though, hello from Belgium.

  36. Actually... by denzacar · · Score: 2, Insightful

    I did read the PP and I've even replied to it.
    And I thought that I was clear enough in my reply, but apparently not.

    See... the game is not most power-efficient cooling, or even best cooling.
    The game is "most bang per buck invested in the server infrastructure".

    Now... Saving money by reducing the cooling costs by using huge passive cooling farms is a nice idea, but not as easily calculable as simply switching to cheaper electricity.
    Sure, should you move your servers to Siberia you would get shitload of passive cooling, but unless polar bears are going to start using broadband internet - servers will never make it above 50% efficiency.
    Cause, even on 100% usage - they will still be in the middle of the f-in desert. No local traffic. Too far from civilization for the global traffic.
    Any money you would save by running those "virtualized workloads" through such power-efficient servers would be overshadowed by higher maintenance costs to the infrastructure and higher energy costs.

    On the other hand - switching to servers running on cheaper electricity at the moment is a quite clear and easily calculable way to save money.

    There is a compromise solution though. Mountains. Don't go north, go up.
    Granted, there are not always readily available, but Europe and USA's west coast are really close to both major internet backbones and mountains.

    Still... You would probably save more by "zone switching" than with passive cooling.

    --
    Mit der Dummheit kämpfen Götter selbst vergebens
    1. Re:Actually... by maharb · · Score: 1

      I hate to flame but you really need to gain some reading comprehension skills.

      1) I have never disagreed with any of your ideas. I find them to be quite correct in theory.

      2) The only thing I was replying to (once again) was about using passive cooling by rerouting traffic to areas where it is night/cooler part of the day. You seem to agree with me on this yet somehow have tried to twist my words and make it seem like I am arguing with you about it.

      3) You have also brought in this cheaper electricity thing which is never mentioned in this thread by anyone but you.

      4) Yes, using cheaper electricity will save money, I never said anything about that.

      I was mainly pointing out the flaws in the parent's post and offered a simple one sentence better solution. You then offered a 3 paragraph solution that included nearly none of same topic that me and parent were talking about. Then you come back again and offer other random points of defense that have nothing to do with this discussion. I should stop now.

      Interestingly enough though you say that putting stuff up north is worthless because its far away from people using it, yet you say that rerouting traffic based on time of day is super efficient. Why can't you just route traffic to the north? I'm not talking on the freaking I ice caps here... I am talking northern europe, canada etc.

      Mountains will work too, good point.

  37. Re:Unreliable...Probably not by Anonymous Coward · · Score: 0

    Ice storage does not work very well for datacenters. Cooling load does not drop significantly at night during the peak week, so you end up having to install significantly more chillers than a normal system to charge the ice bank. Datacenters are usually limited by the MW they can get from the utility, and you don't want to waste an extra 500 kW just on extra connected chiller load to make ice at night. That's watts out of your IT equipment. And ice is much more inefficient to make than just cooling the space directly - a 20F brine is inherently less efficient to produce than 50F chilled water.

  38. Quebec by werfu · · Score: 1

    Why don't they build a data-center in Quebec province? They could build it near the James Bay and have a lof of cool weather plus having really cheap electricity. All they would have to do is build a backbone of fiber to it, which is inland :)