Forgot your password?
typodupeerror
HP Power Hardware

Is a "Net Zero" Data Center Possible? 160

Posted by samzenpus
from the lowering-the-power-bill dept.
miller60 writes "HP Labs is developing a concept for a 'net zero' data center — a facility that combines on-site solar power, fresh air cooling and advanced workload scheduling to operate with no net energy from the utility grid. HP is testing its ideas in a small data center in Palo Alto with a 134kW solar array and four ProLiant servers. The proof-of-concept confronts challenges often seen in solar implementations, including the array's modest capacity and a limited window of generation hours – namely, when the sun shines. HP's approach focuses on boosting server utilization, juggling critical and non-critical loads, and making the most of every hour of solar generation. Can this concept work at scale?"
This discussion has been archived. No new comments can be posted.

Is a "Net Zero" Data Center Possible?

Comments Filter:
  • by khasim (1285) <brandioch.conner@gmail.com> on Thursday May 31, 2012 @12:38AM (#40163625)

    HP is testing its ideas in a small data center in Palo Alto with a 134kW solar array and four ProLiant servers.

    Four servers is a nerd's basement.

    Wouldn't you need something like 4 racks full of servers? Running something like seti@home or distributed.net?

    In its own building.

    • by Anonymous Coward on Thursday May 31, 2012 @01:13AM (#40163797)

      the main thing they're testing is the scheduling of workloads to to get the maximum benefit from their solar array. It doesn't matter how many servers they have. They'll still get useful data from this test.

    • by dbIII (701233) on Thursday May 31, 2012 @01:21AM (#40163831)

      Four servers is a nerd's basement.

      That's where all of HP will fit soon with their current management style.

      • With the current management style, there will be so many reporting tools for middle management left and so few workers, that they'll need more than 4 servers per employee to fill in time sheets and surveys.
    • by jakimfett (2629943) on Thursday May 31, 2012 @01:22AM (#40163839) Homepage Journal

      How is that a test? Four servers is a nerd's basement.

      At the very least, they can do a cost analysis of the setup. Sure, it's only 4 servers. But if it's possible to do with four, then they can extrapolate to forty, or four hundred. Granted, there are things that don't scale perfectly...things like cooling, cost of raised floors, the building itself...but now they have hard data about how many solar panels they need to make it a net electrical drain of zero.

      • by hairyfeet (841228)

        But servers don't have loads only during the day so going with panels would be stupid for servers. you may get away with it with an office but NOT servers.

        If you wanted to power a datacenter off of renewables then a combo of wind and molten salt solar power generation would be a much more logical choice as you can use the salt like a battery to generate power at night and use the wind to also charge batteries to insure that on days without any sun you would still have power. it just seems kinda pointless

      • Being self sufficient is quite handy if you were trying to run within a spaceship for example, but a setup that merely relies on off-grid power such as solar still requires an external source. Pretty much it means if you need to consume lots of power you end up building your own grid (or else figure out how to use less power to compute the same result).

        This month the Top 500 supercomputer list is being updated again, and exaflops is supposed to be just a few years away. This amount of compute speed is proje

    • by mbone (558574)

      HP is testing its ideas in a small data center in Palo Alto with a 134kW solar array and four ProLiant servers.

      Four servers is a nerd's basement.

      I have more than that in my basement. Think I'll get some solar cells and put out a press release.

      • by Sussurros (2457406) on Thursday May 31, 2012 @02:48AM (#40164063)
        You do know that solar panels won't work in the basement...

        I know it's a cheap joke but I'm a cheap kind of guy. My favourite basement of all time is Dean Kamen's (inventor of sedgway, half the equipment in the hospitals, and lots more - our modern day good guy Tesla and bad guy Edison all rolled into one) from his youth.

        When he was a schoolkid he snuck into a museum one night and rewired the lighting of a single section. The next day he applied for the contract to do the whole museum and got laughed out of the door because he was a kid, until he told them to look at the section he had done the previous night. He narrowly avoided arrest and got the contract instead and did an excellent job.

        With the money he earned he paid for a vacation for his parents and while they were away he had the family house removed from its blocks, a huge basement dug then filled with heavy lathes and state of the art engineerng goodies, and then had the house reseated.

        To cover the extent of the cavernous basement he had to install a new patio over the part that the house didn't cover and when his parents came home they were thrilled to see the wonderful new patio he had built for them.

        That was his last year in high school, and I'm sure that a few solar panels and clever power management wouldn't have been enough to run that particular glorious basement.
  • As a net 0, No. It can't work from solar. The amount of electrical storage would make it impracticable.

    However, this is a good idea, not as a net 0, but for cost and sustainability. Having solar during the day would reduce cost and cut down the backup generator requirement. If there is a brown-out/black-out on the power grid, during the day, you have solar. At night you'd still need diesel.

    • Re:No! (Score:5, Insightful)

      by nzac (1822298) on Thursday May 31, 2012 @12:44AM (#40163647)

      As a net 0, No.

      You can both consume power from the grid and produce it. The extra they make during the day that someone else uses is what they use at night.

      Its a PR stunt though, if a bunch of companies got together and funded a massive solar farm it would have the same result and probably be more efficient.

      • by Bert64 (520050)

        Feeding solar in like that just causes inefficiency, you still need the same level of power generation from other (coal/gas etc) sources on the grid to cope with nights and cloudy days.

        • by nzac (1822298)

          Depending on the source they can adjust power output depending on the required power.
          On a sunny day you don't need to burn as much fossil fuels and when its raining you burn the normal amount but overall less hydrocarbons are burnt.

    • by Anonymous Coward

      At night you'd still need diesel.

      If you have "Free extra power" coming in it might be a better idea to to use a rechargeable system like a fuel cell.

    • by PhrstBrn (751463)
      Technically, you can get 24 hour power generation with pure solar energy. Excess power can be stored as molten salts, which can in turn be used on steam turbines during off peak hours. That said, on the micro-scale that the article is talking about, I'm not sure this would even be feasible.
  • Am I the only one (Score:2, Interesting)

    by Anonymous Coward

    That thought this "Net Zero"?

    http://www.netzero.net/

    • by game kid (805301)

      Nope. Fond memories of this TV spot [youtube.com], and the other one with a young man instead of Ms. Blaine (ph), where the "Willy-nilly" guy in the former video says "What you are doing is flagrantly un-American!" and the last syllable sounds kinda like it ends with an "m" instead.

      I still use my Netzero email address as a secondary, and something of a spam catcher.

    • by dgatwood (11270)

      And you could probably run servers on it, but you'd have to use DynDNS or similar.

      But seriously, the cynic in me has to wonder how many of those employees they're about to lay off wouldn't be going away if they hadn't spent who-knows-how-much-money on a server farm that they probably don't actually need. Not that this one project would pay for more than a handful of employee-years by itself, mind you, but such waste rarely occurs in isolation. It's like seeing a termite in your house. You can be fairly

  • ok.... (Score:5, Funny)

    by bhcompy (1877290) on Thursday May 31, 2012 @12:41AM (#40163639)
    Why would my datacenter want freaking banner ads all over it?
  • by DontScotty (978874) on Thursday May 31, 2012 @12:42AM (#40163643) Homepage Journal

    At the equator... then you'd have some uptime!

    • by subreality (157447) on Thursday May 31, 2012 @01:17AM (#40163817)

      I must regretfully inform you that 2/3 of the surface of the planet in question is covered in water, and it's considerably more than that along the line of the equator. Please plan to install 8 or 9 of your data centers on ships.

      For the ones on land you will be choosing from Ecuador, Columbia, Brazil, Gabon, Congo, Kenya, Somalia and Indonesia. I suggest budgeting for a considerable number of guns.

      I personally think people over-A/C most data centers (computers really don't care if it gets kind of warm; they only really care about temperatures that their human slaves would object to), but in these places... well, I hope you're friends with Carrier.

      But all these problems can be overcome. I'm sure you'll do well with the abundant free sunshine!

      • by MiniMike (234881)

        How about two data centers- one at each pole? Each one would have 6 months of sunlight, although probably at a high air mass. Cooling would not be much of a problem, some of that heat might even be appreciated (first data center to request P4's?). You might need weapons to defend against polar bears (if the North Pole ice is thick enough), but fewer than to defend a data center in any of the areas mentioned above. The penguins at the South Pole might be a welcome sight. I don't think the connectivity p

      • by habig (12787)

        I personally think people over-A/C most data centers (computers really don't care if it gets kind of warm; they only really care about temperatures that their human slaves would object to), but in these places... well, I hope you're friends with Carrier.

        I've never understood why data centers aren't built exclusively in cold-weather locations. I live in Duluth, MN, and if we turn on our AC (for humans) more than about a week a year it's considered an awful heat wave. During the majority of the year, all the heat being pulled from the servers could be used to provide heat for nearby humans, something they're paying for anyway.

        So: pay for the electricity (from whatever source) only once (to power the boxes), instead of twice (power the boxes and the compres

      • by unixisc (2429386)

        Skip Somalia and Indonesia, but have it in Ecuador, Colombia, Brazil, Gabon, Congo (I'm guessing one means the former Zaire), Uganda (which you missed) and Kenya. Also, since we are talking about the equatorial regions and not merely the equator itself, countries like Guyana, Suriname, Cameroon, Central African Republic, Ethiopia, Sri Lanka, Thailand, Cambodia, Vietnam, Philippines and Papua New Guinea can be added as well. Not sure whether South Sudan is stable and safe from a Sudanese invasion, but if i

  • They're actually building it into a genius bitcoin mining mega-rig! No overhead for utilities?! They're rich! Okay, just kidding...although I didn't see any evidence that they're not, lol.

    P.S. my electric costs were $40/mo and my bitcoin income from it was around $54 so yeah....but FPGA miners can run at 14W and can alone hit 0.63x the performance of my own Radeon card rig (which ran at around 480W). So setting aside the bitcoin mining joke, no matter what they're using the place for, eliminating the
  • Silly headline (Score:4, Insightful)

    by DoofusOfDeath (636671) on Thursday May 31, 2012 @12:47AM (#40163669)

    If you're already assuming that a data center can include its own power generation systems (solar, wind, hamsters, etc.), then of course it's possible.

    Just include a local coal or nuclear plant on the datacenter's property. Or, if the "renewable" detail is critical, create one in the middle of the Mojave dessert, with 30 sq. miles of solar panels, which during the sunny times also charge up a 400-ton array of lithion-ion batteries or a flywheel generator.

    So I wonder if "possible" is really what you're asking.

    • Yes, it's also possible that it's the answer to the age old question "why are we hear?" - to build a Dyson sphere data center around the Sun!
    • by lakeland (218447) <lakeland@acm.org> on Thursday May 31, 2012 @02:19AM (#40163989) Homepage

      You can pass the excess power on to the grid according to the definitions they're using. As long is you've given more power to the grid than you've taken out, you're a winner.

  • by Karmashock (2415832) on Thursday May 31, 2012 @01:06AM (#40163757)

    You can't build something that will do the same job but not economically. These will remain concepts and prototypes until we can get a solar cell that is very efficient at a competitive price.

    I wish this weren't the case... who likes being a slave to the grid but no one is making solar sustainable without absurd subsidies. The germans are making a big push for it right now which can only go to sad places because germany isn't known for it's sun and has huge energy needs. I wish them well and I hope I'm wrong... but it's looking to implode as soon as the maintenance costs start ramping up. We know a little about this in california. We've been building these sorts of power plants for decades. They work fine initially. But five years down the road everything goes pear shaped and you have another eco ruin in the desert.

    • Does anyone know the theoretical maximum output of solar energy per square foot? You only get so much energy hitting the ground, so it may not even be possible with a 100% efficient solar cell. Just throwing that out there.
      • Depends entirely on the surface area. The point with solar is to make it work you need to be able to cover a HUGE surface area. If you covered the whole state of Nevada with solar cells we could probably feed total US electrical demand and then some. But short of that it's a waste of time.

        If we can make it cheap then we can put it on every roof and at least reduce everyone's energy demand. But the price has to be very very low or it won't make any sense. It's not just the cost of the cells it's the installa

        • Does anyone know the theoretical maximum output of solar energy per square foot? You only get so much energy hitting the ground, so it may not even be possible with a 100% efficient solar cell. Just throwing that out there.

          Depends entirely on the surface area. The point with solar is to make it work you need to be able to cover a HUGE surface area. If you covered the whole state of Nevada with solar cells we could probably feed total US electrical demand and then some. But short of that it's a waste of time.

          That was kind of my point.

          • you asked a question... questions aren't points... ;-)

            • And you didn't answer it.
              • roughly 1 kWh at sea level per square meter.

                The city of Los Angeles consumes about 6000 MWh every day.

                So to meet that demand you'd need about 6 million square meters of solar cells to meet the demand for los angeles. That is six square kilometers of solar cells. Probably a good idea to increase that by about 40 percent just because the cells aren't going to be RIGHT next to each other and there's likely to be wasted space. Additionally, the DWP has over 7000 MWh on tap at any given time so ideally you'd wan

        • by nmos (25822)

          I can't help but wonder when this will collide with "Smart Growth" which is a push in many communities to cram more people into smaller areas surrounded by open space as an alternative to urban sprawl.

          • Green belts have been around for ages...

            As to solar, I think the best solution is a two part system.

            This assumes the technology is ready and I don't think it is yet. But use low efficency, cheap, and robust solar cells in deserts or other unpopulated areas with good sun. This should provide the bulk of our power needs. On top of that, put higher efficiency solar cells on top of roofs throughout urban areas. These should probably be owned by the power utility. By all means, let people buy them but most peopl

      • Does anyone know the theoretical maximum output of solar energy per square foot?

        About 120W/ft^2, assuming ~100% efficiency.

        With current technology, we're talking maybe 25W/ft^2.

        • Interresting, so with current technology, a typical home computer (300W) would need 12ft^ of solar panels to run. If it ran 24x7 (powerful home server) you'd need 24ft^ - 30ft^ to compensate for darker hours of the day if you wanted to go for 0-net power. For home use, that sounds very workable (unless you live in an appartment), but still fairly infeasible for server farms unless you have a few dozen acres of empty land next to the facility.
      • by rasmusbr (2186518)

        It really depends on where you live. For example if you live north of the Arctic circle the average daily insolation is zero during much of the year... But most people don't, fortunately.

        If we assume that we're going to have about 10 billion people living middle class lifestyles then we're going to have to cover on the order of 1% to 10% of the world's surface area with solar cells depending on how efficient the solar cells are and how efficient your grid and energy storage is, and on how efficient our home

        • We don't need planetary energy storage, there's always SOME area of the eart that is in darkness and needs more power.
  • Really, this idea has lots of warm fuzzy, but it won't work as a general industry practice.

    Take my current location: last summer we had epic heatwaves of triple digit ambient daytime temps. Using open air cooling those servers would be actively overheating just by being turned on, let alone running code. Generating their own heat, they would risk serious failures. In palo alto, where they have a cooling ocean breeze blowing inland and moderating summer temperatures, it might work. In the landlocked hellho

    • DC to DC conversions can be done with 95+ % efficiency. Convert it to 10 MHz, push it to a high efficiency transformer (those are easy at these freqs) at 99% efficiency and convert it back to DC (at high voltage the 0.7 V of a diode isn't a big drop). It costs energy, but not that much.
  • No this concept can't work at scale - 130KW means around 10,000 sq ft of solar panels -- all to power 4 blade servers. If they were in a c3000 enclosure, they could put 8 blades in 6U - so could fit 56 blades in a 42U rack.

    If they need 130KW and 10,000 sq feet of solar panels to power 4 blades, they'd need 14 times more panels to power a 56 blades in a full rack, or 140,000 sq feet of panels, all to power 6 sq feet of servers.

    So a small 12,000 sq foot datacenter can hold around 1000 times more servers, so y

    • by Entropius (188861)

      Why the heck do you need 130KW for 4 blade servers?

      • by aXis100 (690904)

        Because the sun only shines for about 4 peak-equivalent hours per day, so that 130KW peak array only produces enough to support a constant 21KW load.

        Next you have to realise that whatever power the servers are using will end up as heat, which also has to be removed from the building with an AC system.

        Still, even half of that at 10kW would seem pretty high for 4 servers.

  • by subreality (157447) on Thursday May 31, 2012 @01:23AM (#40163845)

    ... Then the answer is probably no. I used to stack Dells floor to ceiling in the racks and never had a problem with power. Just interleave a PDU every so often and plug 'em all in.

    Then I got a job at an HP shop. Started putting DL360s and DL380s in a rack. Breaker pops. Break out the clamp meter. No, the breaker's no defective. Those things GUZZLED. I have no idea what they did with the extra juice.

    Anyway, if that's what they're using, they should forget about it. But perhaps their hardware has improved since then. People are paying more attention to power these days.

  • by mbone (558574) on Thursday May 31, 2012 @02:03AM (#40163953)

    Can this concept work at scale?"

    Almost anything can be done if you don't care what it costs. What I don't see here (or in the similar Apple and Google announcements) is any indication of what their cost target is. Does anyone have any idea what their electricity costs need to be (or what the average datacenter revenue per megaWatt is)?

    • by kenh (9056)

      Please spec out a 134Kw solar array - I think you are looking at about a 10,000 square foot array - to power and cool FOUR servers at a cost of around a quarter million dollars (before incentives and subsidies).

      Uh, I don't think this will scale.

      What would it take to power a Sun "Datacenter in a Box" with it's 600 Amp, 208V three phase power requirement from solar panels? That would be a good indication of this concept's ability to "scale"...

  • Solar panel costs (Score:3, Insightful)

    by HuguesT (84078) on Thursday May 31, 2012 @02:59AM (#40164089)

    Does this experience account for the solar panel manufacturing costs and their environmental footprint as well? Even the most optimistic [sciencedaily.com] studies admit it is not zero.

  • I haven't heard about that ISP for long time, no they are building a Data Center! It's amazing some of the things the things I don't hear about.
  • by Lord Lode (1290856) on Thursday May 31, 2012 @07:04AM (#40164835)

    Sure it's possible to have a Net Zero datacenter: Just use unary coding instead of binary, with 0 as the unary digit.

    For example, by binary number 101 would become as 00000.

    See? As a result, all the bits will be zero. Net zero. That means the data will weigh less, and it's good for the environment! A win for everyone.

  • We run a datacenter in a LEEDS Platinum building...

    http://www.nrel.gov/news/features/feature_detail.cfm/feature_id=1505 [nrel.gov]

  • 1. Spend $X buying bonds
    2. Use a portion of the interest to pay electricity bill.
    3. Re-invest remainder.

    For some value of X, you will earn enough in interest to pay your energy bills.

    X will *certainly* be less than the amount of money required to build your own mini-power generation facility. I understand the need for on-site emergency backup, but in terms of day-to-day operation, your own boutique power plant will be more expensive than buying power at market price from the grid.

    Economies of scale, people

    • by nmos (25822)

      That's only true if the rate of interest on the bonds exceeds the rate of increase in energy costs. That seems unlikely today.

  • Usually that's what we call a guy with a CCNA and no real-world experience.
  • First off, the four servers are "fairly" beefy - four servers, each with dual 12-core CPUs, 64 Gig RAM, etc. and their datacenter include cooling (running air conditioning off of a solar arry seems like a bad idea, kinda like running a laser printer off battery power)...

    If you really wanted to shoot for zero power from the grid, rather than throwing a huge solar Array at powering (and cooling) four big servers, why not re-engineer the datacenter to require less power all together? If we have to pack a dozen

  • a net zero data farm is actually trivial. Just mount up (x) acres with solar arrays and vanadium redox batteries (for night time) and bingo - you gots a net zero data farm.

    Where the rubber meets the road is: ? can solar (and similar energy sources) power the machines in Congo that dig the coltan out of the ground for the warlords to sell to ICT companies, and can solar (and similar energy sources) power the machines that build the ICT machines in the data center, including smelting the aluminum out of the

  • The should of gotten Carly Fiorina to power the data center using all her hot air. They clearly missed the boat.

No hardware designer should be allowed to produce any piece of hardware until three software guys have signed off for it. -- Andy Tanenbaum

Working...