AC and DC Battle For Data Center Efficiency Crown

Makes sense. by Anonymous Coward · 2012-03-14 08:30 · Score: 5, Interesting

AC is better than DC for transporting electricity because you can convert between voltages with just a transformer. But in a data centre, when all the equipment will be powered by the same voltage, it makes sense to use one good efficient power supply for multiple computers, so that all the components don't have to be duplicated for each computer.

Re:Makes sense. by Microlith · 2012-03-14 08:39 · Score: 3, Insightful

As opposed to the transformer coming into your building? How about the UPS and HVAC units supporting your server room?
Obviously, you'll have redundant DC power supplies, just like you do now. Except instead of having two AC->DC power supplies per PC, you'll route two room-level DC power supplies to each machine in the room. Lots of little, less efficient, lower quality power supplies replaced by a pair of high quality, high efficiency supplies.
Re:Makes sense. by Imagix · 2012-03-14 08:40 · Score: 3, Interesting

Because you've immediately forgotten the concept of redundant power supplies? In a rack of 48 1U computers, that could be 96 AC-DC converters. Or replace those 96 with 2 (or 3, or 4, depending on risk tolerance) big, high-efficiency AC-DC converters. Better efficiency, easier to cool.
Re:Makes sense. by gparent · 2012-03-14 08:41 · Score: 2

Yeah, it'll be just like network routers and switch that always bring down the whole network with them! If only there was some way to prevent single points of failure...
Re:Makes sense. by betterunixthanunix · 2012-03-14 08:42 · Score: 4, Informative

AC is better than DC for transporting electricity because you can convert between voltages with just a transformer.
Which was a winning argument in the 19th century, but not anymore. The use of AC entails significant power loses, especially for cables that are immersed in salt water, which is why DC is used in such situations:

https://en.wikipedia.org/wiki/High_voltage_direct_current

--
Palm trees and 8
Re:Makes sense. by tlhIngan · 2012-03-14 08:43 · Score: 4, Informative

AC is better than DC for transporting electricity because you can convert between voltages with just a transformer. But in a data centre, when all the equipment will be powered by the same voltage, it makes sense to use one good efficient power supply for multiple computers, so that all the components don't have to be duplicated for each computer.
It depends.
AC wins out because of ease of conversion, becaues the higher the voltage, the lower the current, and lower the current, the lower the IIR losses in the wire. DC didn't win because at the time, efficient (and cheap) voltage converters didn't exist. These days, a switching DC-DC supply can easily exceed 90% efficiency, and you can get solid-state converters that can handle transmission line powers easily. Hence the launching of HVDC transmission lines which don't have resonant losses and no phasing issues
In a datacenter, you'd probably take the incoming power and turn it into an intermediate voltage like 48VDC per rack or something - something that minimizes IIR losses (you want high voltages) and DC-DC converter losses (ideally you want output voltage and no converter).
It will have to be per-rack at the minimum purely because of the losses - if we did 12V lines and a few servers take 1200W total, we're talking 100A in current If we bump it to 48V, we're dealing with 25A (maybe 30A after inefficiencies), and IIR losses at 25A are lower than at 100A (it increases with the square of the current).
Also, the 100A cables are big and chunky (which you need because they reduce the "R" part of IIR losses).
Re:Makes sense. by effigiate · 2012-03-14 08:55 · Score: 5, Informative

One of the challenges of HVDC, especially in the transmission/distribution world, is that normal switching happens on the line and not at the breaker. If you can switch futher down the line, you can leave all the people closer to the breaker with power. The issue is that this switching happens while current is flowing which requires that the device interrupts real current. In the AC system this is relatively easy because the arc created by opening a high voltage circuit under load goes out at every current zero. There is no current zero on DC, so you force the interrupting device to break current. An similar situation can be seen if you look at relay contacts. They may be rated at 20A @120VAC but only 0.5A at 12VDC.
Re:Makes sense. by vlm · 2012-03-14 09:06 · Score: 2

AC is better than DC for transporting electricity because you can convert between voltages with just a transformer.
Not anymore. The greenies / cost cutting / etc means no more xfrmrs anymore. Bye bye to that technology. Whens the last time you bought a wall wart charged device with a transformer inside it (you'd know, it'll be cubical and heavy)? You have to be pretty old by /. terms to have bought a main desktop computer without a switcher, like early 1980s era pre-PC "home computers"... Ahh the old Altair with its smoking hot 7805 regulators...
Since you're gonna have a switching power supply anyway... why not skip the pesky rectifier diodes and feed in raw couple hundred volts DC? Quite a few PC power supplies work just fine off raw DC on the supposed "AC input"... good luck figuring out which work and which dont without some smoke events.
I can save everybody a lot of time by posting the summary from the last 50 /. discussions of DC data centers:
1) RMS voltage is always going to be lower than peak... insulation is cheaper, or for a given grade of insulation you can push more wattage in DC.
2) Switchgear is complicated. Labor cost goes up.
3) Expect the fire marshall to completely flip his lid unless he's up with the times.

--
"Science flies us to the moon. Religion flies us into buildings." - Victor Stenger
Re:Makes sense. by Skapare · 2012-03-14 09:33 · Score: 3, Interesting

And a big disaster waiting to happen with such large DC currents available on all the busses going all over the room. FYI, telco 48VDC systems addressed the dangers with resistive busses. But that was a huge efficiency loss. They didn't care so much about efficiency back then as all they wanted was a reliable battery backed up system. Making DC efficient is also making DC unsafe, at data center scale. AC is safer on that scale. Then do the conversion to DC at no larger than one rack, and put ride-through (2 minute) backup batteries in each rack (just need to be long enough for slow start generators or maybe a little longer for diversity loading systems so you don't slam the generators with load). I'd have a separate AC distribution system for the generator power and have each (two input) power converter switch over at randomized times over a 2 minute interval.

--
now we need to go OSS in diesel cars
Re:Makes sense. by nschubach · 2012-03-14 10:38 · Score: 3, Insightful

I'm more concerned that I convert AC to DC to charge a battery, then convert it back to AC to power a power supply in my machine that outputs DC voltage. (Or, taking the DC battery output and inverting it to AC to run a computer.) Why can't I just run my PC off a battery that's kept charged by a DC current from a single power supply? I mean, I don't need the efficiency of AC for long distance transfer (we're talking maybe 3 feet) so why convert it back to AC?

--
Every time I start to have faith in humanity, I ruin it by driving to work between 7 and 8 am.
Re:Makes sense. by Nethead · 2012-03-14 10:44 · Score: 3, Informative

The last two data centers (Clearwire) I built out were DC. The only AC in the cage was for a video monitor and for the tech's wifi router. Very standard stuff, the telcos have always done it that way. Any bit of Cisco/Juniper/whatever kits can be ordered with DC power supplies. I see DC plants as more the standard now. And yes, the are still built using waxed string.
Even Power over Ethernet has it roots in telco -48VDC power. All the WAPs and fiber converters at a Lowe's are powered by a Valare DC power supply ( http://www.power-solutions.com/dc-power-systems/eltek-valere.php ).
One nice thing about DC plants are the power cables are cut to length so you don't have all that extra line cord to bundle and hide.

--
-- I have a private email server in my basement.
Re:Makes sense. by EdIII · 2012-03-14 10:53 · Score: 2

Thank you. This is why the debate always confuses me. The poster is not exactly trolling. A single AC-DC power converter is a single point of failure, which is bad. Typically you have two, or even three, power supplies on most servers.
In my data center the AC is very clean, redundant, and has diesel fail over. Now if that is considered to be reliable, and as one poster suggested, we could use backup batteries for only a minute or two, why not convert all of the servers and supporting hardware to DC inputs and dump the AC-DC converters?
If you wanted to still make it redundant, you could build a 2U dual high-efficiency AC-DC converter with battery backup. That should be pretty reliable.
The benefit would be an easier hand off for power from the data center. You don't need expensive power strips taking up space and you can dump all of the power supplies in the rest of the equipment. Just agree on a standardized connector and even color code it to voltage.
It has never made sense to me in a data center setting to have that much space occupied by AC-DC converters.
Re:Makes sense. by aaarrrgggh · 2012-03-14 11:35 · Score: 2

The best DC approach is 500+V DC distribution to the rack. The best AC approach is 400V to the rack. Either approach uses redundant low voltage power supplies at the rack level.
The benefit of DC is that you can stick dumb batteries on the bus (with an in-line charger) which eliminates a conversion to AC that would be required from a traditional static UPS.
On AC, the energy saving strategy is different-- do as little work as possible for as much time as possible, and run on "dirty" power until it is really bad. Or, you can use an AC flywheel.
From a distribution perspective, you can get 90% efficiency compared to a traditional 75% for a 480V double-conversion UPS going to a 120/208V PDU.
Then at the rack level you address power supply efficiency.
Re:Makes sense. by Mabhatter · 2012-03-14 11:44 · Score: 2

That's basically what Blades are right now. Effectively, Blades already exist because treating rack servers the same as a herd of Boxen has been silly for a while.
Ideally, you would have a "rack level" spec where DC power would be on tap maybe at the rack level, with the "ATX" DC connector (maybe even 3,6, & 12 volts) going out the back of the server.
The problem right now is that if you're not Google and can get boards and cases shipped from the factory like that, there is no spec so "little people" can do this. There ate still a lot of redundant electronics that could be pulled out of even blades... For instance the famous Capacitor problems...Imagine how many of those Google had to deal with! Why not move all those parts to the rack as well?
Of course what somebody like Google really wants is for OEMS to split the standard server mainboard at the power junctions and io ports. So you can buy one board or ten or thirty and slide them into whatever enclosure you need with minimal extra parts.
For example Apple has the Mac Mini down to where it just needs DC in and the Thunderbolt port to be functional.
Re:Makes sense. by drinkypoo · 2012-03-14 12:19 · Score: 2

It doesn't really work that way. A battery charger is just a power supply. When the battery is charged the charger outputs maintenance voltage and your computer is really running off the charger. When the battery is not charged the charger puts out charging voltage, and your computer is really running off the charger. When the mains current cuts out your computer just runs off the battery. This is a UPS, as opposed to a SPS where you run on mains and then switch to the inverter in case of a failure and hope the power supply caps let you ride out the switchover time, which is a reasonable assumption unless your power supply is about to go tits up anyway. UPS costs more than SPS because you need enough charger to provide maximum output and to at least trickle charge the battery at the same time, especially true when the battery chemistry is not conducive to being discharged for long periods.

--
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"

Not really by Anonymous Coward · 2012-03-14 08:39 · Score: 2

which means that most modern data centers today run on AC power

Only if you ignore all telecom equipment which have run on -48VDC for decades. True, they're not really 'data centers' but it's not like they don't use massive amounts of electricity.

Yay, another volt standard... by mlts · 2012-03-14 08:42 · Score: 4, Informative

There was an article about using 380 volts a couple weeks ago on /. in the data center.

Having DC brings some benefits, mainly just needing to step down voltage and not have to rectify it smoothly with capacitors to even out the output current.

However, there are some downsides:

1: AC power supplies in devices tend to be more tolerant of power fluctuations. An all DC shop might completely be halted by a power surge/spike that wouldn't bother a data center on AC.

2: DC sparks a lot when connecting/disconnecting. AC has plenty of zero-crossings a second (120 or so), so it won't make the fireworks show when plugging/unplugging. This makes switches rated for DC a lot more expensive than AC.

3: There is no such thing as a NEMA 380VDC connector. So, either items would have to be wired up to a bus bar similar to how 48VDC telco stuff gets, or it will end up like 12VDC with at least 5+ connectors (direct wires, cig lighter, airplane, marine connector, male/female combined connector, motorcycle accessory connector, banana plugs.)

4: Safety. 12 VDC shocks are annoying; a shock from 380VDC will be fatal, especially because of DC's tendency to get muscles to "lock". (This is why stun fences uses AC, while kill electric fences use DC so they can keep the target locked on the wires long enough to get the amps across the heart.)

5: Issues with wire length. AC, it isn't hard to use a transformer to deal with voltage drop. DC, that will be a lot harder.

All and all, 380VDC seems like a solution in search for a problem. We really don't need another standard. Heck, just pointing out 120VAC in the US means I have to doublecheck if I'm dealing with 15 amps, 20 amps, 30 amps, or 50 amps, and the locking versions of each, which means six plug types and minimum wire gauges.

Re:Yay, another volt standard... by subreality · 2012-03-14 23:09 · Score: 2

So you'll handle it much like most hotplug PC hardware is these days, with latches and mechanical disconnects that ensure + and - are disconnected simultaneously.
You don't want to disconnect both simultaneously. The idea is to disconnect + first and leave ground connected. The voltage across the whole component falls to ground level instead of potentially floating up to + briefly.
This is a different problem from what the GP was talking about: When you hot-unplug a device drawing lots of DC, it starts to draw an arc. The arc will continue to draw until it gets too long to be stable, forms a big rainbow, and then extinguishes itself. The distance depends on the voltage. Thus you need non-mechanical, solid-state ways to shut off the current, or mechanical switches with an arc-extinguishing enclosure for really big applications like transmission lines.
When you hot-unplug a device on AC, it starts to draw an arc, but within 1/120 of a second the current (possibly a little out of phase with voltage) will cross zero, thus extinguishing the arc; and it won't reignite except if the contacts are VERY close and then will promptly be extinguished again on the next cycle.

6 one way, half a dozen the other by thsths · 2012-03-14 08:46 · Score: 4, Interesting

AC, DC, it does not make a difference any more. Yes, you have to rectify AC before it powers a computer, but the rectification costs less than 1% of the energy. Power factor compensation can be more costly, but it could be avoided by going to a 3 phase rectifier. There are also serious distribution advantages in 3 phase electricity, but it is not used because of the extra complexity, despite being cheap.

DC distribution is expensive, and 1% gain is just not enough to pay for it. Once we have intelligent grids, the situation may be different, but for now there is just no business case.

You're gonna spend your savings on copper by ZorinLynx · 2012-03-14 08:47 · Score: 3, Interesting

Standard -48VDC current distribution requires four times the current as 208V AC distribution for the same amount of power. Have you seen DC cabling at data centers that use it? If we're going to start using DC in data centers we need to come up with a higher voltage standard, otherwise we're going to spend all the savings on more copper (which is expensive!) to carry those extra amps.

Re:Yes, but by KBehemoth · 2012-03-14 08:50 · Score: 3, Funny

The appropriate demo of the dangers of AC data center power will be to show an elephant losing his entire database due to a power failure. Ominous voiceover: "Unlike an elephant... AC-driven data centers always forget!"

Edison invented FUD by Thud457 · 2012-03-14 08:53 · Score: 3, Funny

Thank god, I'm so tired of stray dogs wandering into my datamacenter and getting electromacuted by deadly AC currents!
Peta's really on our asses about that.

--

the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff

Re:Edison invented FUD by Mashiki · 2012-03-14 09:14 · Score: 3, Informative

Well if you live in Toronto, there's a very good chance that simply walking down the street you could get electrocuted by well anything. I'm not actually kidding, they had a serious problem with live plates and poles all over the city for the last couple of years.

--
Om, nomnomnom...

Slashad by Shadowhawk · 2012-03-14 08:55 · Score: 3, Insightful

Articles main source says modern AC and theoretical DC are about the same. By the way, he has a product to sell...

--
My mind works like lightning. One brilliant flash and it is gone.

This is New? by Pontiac · 2012-03-14 08:58 · Score: 2

In 2005 we started looking at blade chassis and tested a rack of HP BL series blades.

That system came with a 48v DC power enclosure with 6 hot swap power supplies. It sat in the bottom of the rack and had a buss bar system to feed every chassis in the rack.

As others have stated.. 48v is a long standing standard for telecom power.

--
If you think it's expensive to hire a professional to do the job, wait until you hire an amateur. --Red Adair

Re:This is New? by Skapare · 2012-03-14 09:14 · Score: 2

But 48VDC also means dual conversion. Convert the AC to 48VDC, then do the conversion again with the PSU in each chassis. You have to get both conversions to be very, very efficient to make that worthwhile.
Everything from Cisco can be had with 240VAC. Very little telco equipment these days actually requires a 48VDC power source. And most of that is for telcos, not for web site providers (for example). And where big network providers do need some 48VDC-only equipment, that can usually be put in the northeast corner of the room and limited in current.

--
now we need to go OSS in diesel cars

I'll stick with AC through the data center and... by Skapare · 2012-03-14 09:08 · Score: 2

... convert that AC to DC at a "blade rack". That would be a rack designed to take blades. But the blades would be a mix of

Processor blades (mostly)
Power conversion blades
Battery backup blades

This will safely segment the power, leaving the DC busses limited to the amperage needed for one rack ... or even partial rack. It also has the flexibility of balancing power conversion vs. 1st tier power backup (at the point of use). Increasing the backup times to a couple minutes allows slow start generators, which are more reliable.

I would run 416/240 three phase everywhere in the data center (even in North America ... transformers for this are readily available). Where equipment isn't on the DC system, run it on 240VLN. The AC/DC converters might run on 240VLN or 416VLL. In countries with 400/230 or 380/220, just use it that way direct.

AC is safer due to the zero crossing. Circuit breakers can break a lot more power (usually 5x the voltage) with the advantage of AC, as compared to DC. A 380VDC breaker for a rack would be HUGE, especially if it has to handle a data center level of fault current.

--
now we need to go OSS in diesel cars

The side that wins the current wars will be by sconeu · 2012-03-14 09:17 · Score: 2

whichever one gets Dirty Deeds Done Dirt Cheap

--
General Relativity: Space-time tells matter where to go; Matter tells space-time what shape to be.

Re:Actually converting DC is pretty easy these day by marcosdumay · 2012-03-14 09:32 · Score: 4, Interesting

You are getting that wrong. DC can be transmitted farther than AC. DC has only resistive losses, while AC also has capacitive and inductive ones.

I'd sumarize it as the following:

DC is slighlty (just slightly) better for transmitting;
AC was easier to convert from one tension to the other (currently, we have the oposite situation);
AC is better to use on motors (it was much better, now it is just slightly better);
AC is easier to generate (it was much better, now it is just slightly better - except on photovoltaics);
AC is easier on the connectors (hight current DC connectors are a hell to maintain)

It is easy to see why AC won. I bet AC would win again just because of the connectors and generators, after all, converting it to DC is relatively cheap. The only problem is the low frequencies we currently use, it would be better to increase them a lot now that we have better materials.

--
Rethinking email

Verari Systems by sdguero · 2012-03-14 09:49 · Score: 4, Interesting

I worked there for 7 years. I'm not going to get into specifics but I will say:

Verari tried to take advantage of the efficiency gains in DC with exotic power supplies etc... And that company went the way of the dodo bird after trying to force 800V, 48V, and 12V DC power distribution systems in customer data centers. The fact is, everything already out there (switches, routers, servers, etc) uses AC-DC power supplies in each unit and it works in 99% of power outlets with pretty good uptime. The added complexity of running DC infrastructure isn't worth the efficiency gains (which on paper sound like a lot but theory rarely translates to reality the way we think it will), and when one DC rectifier burns up and takes down a hundred servers (vs 1 server with an AC-DC supply), customers aren't happy. Between the uptime issues and employee safety concerns (high amperage DC power is more dangerous than AC for a variety of reasons) it's also a liability nightmare

Again, I don't feel like getting into specifics but modern datacenters != underground telco installations and DC power distribution has a LOT of challenges that are often overlooked when marketing types start squawking about efficiency gains.

Did anyone RTFA? by goombah99 · 2012-03-14 09:59 · Score: 3, Informative

Uh the article the post links to supports AC more than DC in case no one noticed. The article is about DC being hyped beyond the facts and that AC is claimed to be just as good. Sort of reverses the whole discussion here making it AD, alternating discussion. Edison gets the carbonite filament..

--
Some drink at the fountain of knowledge. Others just gargle.

Auuuuuughh! by Anonymous Coward · 2012-03-14 11:04 · Score: 2, Funny

Must... unimagine... Tesla... frenching... Edison...

DC advocates trying to get on the same page by 1sockchuck · 2012-03-14 11:07 · Score: 3, Informative

The effort to gain acceptance for DC distribution in data centers is being helped by a series of investments by ABB, and the growth of the EMerge Alliance, which is trying to unify DC proponents around a 380V standard. The challenge for DC is that customers don't ask for it, meaning multi-tenant facilities aren't likely to offer it. Also, Schneider says it is "not aware of any data centers moving off of their established, traditional power distribution to DC." In fact, NTT has at least five DC data centers in Japan, and ABB is backing a DC distribution project at a Swiss hosting company. In the US, there are numerous sites testing DC power, which is widely used in telecom infrastructure.

Re:What voltage would you use? by Anonymous Coward · 2012-03-14 15:18 · Score: 2, Interesting

Actually, 240V, 1kHz would be a lot more efficient, and make power supplies cheaper and more robust to boot.

Slashdot Mirror

AC and DC Battle For Data Center Efficiency Crown

34 of 168 comments (clear)