Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Data centers are transitioning from AC to DC

spectrum.ieee.org

Post reply on HN
Print view View original

411–420 of 432 posts

Re: Data centers are transitioning from AC to DC

#411

Post by ProllyInfamous »

poemxo wrote: post #303
pjdesno wrote: post #227

90% of the power in our academic data center goes 13.8kV 3-phase -> 400v 3-phase, and then the machines run directly from one leg to neutral (230v). One transformer step, no UPS losses, and the server power supplies are more efficient at EU voltages. But what about availability? If you ask most of our users whether they’d prefer 4 9s of availability or 10% more money to spend on CPUs, they choose the CPUs. We asked t…

Really you're down for over an hour a year? Unscheduled?

I was part of an electrician team renovating a three-letter agency's main data center (adding UPS to an archaic government renovation). As part of this process, we had to isolate the Emergency Power Off system/buttons.

Unfortunately, the EPO ended up having been installed differently than the plans indicated [0] — there was definitely more than an hour of unexpected downtime figuring out how to "unrig" its decades of faithful misconfiguration.

During this same months-long modernization, a separate facility decided to install a temporary tap off our already-temporary taps (no engineering consultation attempted) — with resulting Megawatts of melting disaster. More hours downtime.

tl;dr: shit happens

[0] EPO's main neutral was tied into a general lighting circuit's j-box, some bullshit jerryrigging from an 80s sparkie; our apprentice was tasked with taking out old fluorescents... ended up taking out entire facility (through no fault of his own).

Re: Data centers are transitioning from AC to DC

#412

Post by jcalvinowens »

Dylan16807 wrote: post #365
crote wrote: post #328

Earlier quoted context omitted.

In the EU it is quite common for houses to have three-phase power. If you squint a bit, the grounded neutral of the Y transformer isn't entirely unlike the grounded center tap in the US. The voltage is a lot higher, of course!

> If you squint a bit, the grounded neutral of the Y transformer isn't entirely unlike the grounded center tap in the US. Yes, but you only get the safety benefit on three phase equipment. In the US there aren't a lot of 240V plugs, but if you get some installed you can get the safety benefits with plain old consumer goods.

> but you only get the safety benefit on three phase equipment.

The wye ground is beneficial even if there are no three phase loads, because the line-ground voltage is 1/sqrt(3) and you can use cheaper switchgear.

The 3-phase alternative to a wye ground is a corner ground (grounding a live phase of a delta secondary), which isn't done in modern installations because ground faults are full line-line voltage and you need more expensive switchgear.

Line-line faults are always interrupted by two breakers on a wye grounded 3 phase system. But with a corner ground, one breaker potentially has to break the full line voltage for a line-ground fault (you can't fuse the grounded phase).

Re: Data centers are transitioning from AC to DC

#413

Post by jcalvinowens »

zahlman wrote: post #336
jcalvinowens wrote: post #110

Earlier quoted context omitted.

I wired a UK kettle to an unused 240V range outlet in the US once. It was amazing, boiled a liter of water in just under a minute. Obviously kinda sketchy.

"Wired"? ...There was some kind of switch involved, I hope?

I just meant I spliced the line cord, adapters don't exist. It was an easily accessible NEMA 10-50 outlet, so we simply unplugged it when we weren't actively using it, because of the obvious fire hazard of a 16awg line cord on a 50amp breaker (which is why adapters don't exist).

Gratuitous disclaimer, don't try this at home kids...

Re: Data centers are transitioning from AC to DC

#414

Post by Dylan16807 »

jcalvinowens wrote: post #412
Dylan16807 wrote: post #365

Earlier quoted context omitted.

> If you squint a bit, the grounded neutral of the Y transformer isn't entirely unlike the grounded center tap in the US. Yes, but you only get the safety benefit on three phase equipment. In the US there aren't a lot of 240V plugs, but if you get some installed you can get the safety benefits with plain old consumer goods.

> but you only get the safety benefit on three phase equipment. The wye ground is beneficial even if there are no three phase loads, because the line-ground voltage is 1/sqrt(3) and you can use cheaper switchgear. The 3-phase alternative to a wye ground is a corner ground (grounding a live phase of a delta secondary), which isn't done in modern installations because ground faults are full line-line voltage and you ne…

I'm not talking about the safety of different ways of doing three phase. I'm taking it as a given that three phase is wye ground and optimal for safety.

My point is that in the context of a 230V single phase circuit, your ground is no longer in the middle. The ground is on one end of your single phase. If you want a safer single phase, you need to rebalance it to +115 and -115.

Re: Data centers are transitioning from AC to DC

#415

Post by rdtsc »

contravariant wrote: post #407
rdtsc wrote: post #135

Earlier quoted context omitted.

It is a pretty clever design > When it is detected that the PDB starts to detach from the interface, the hot-swap controller quickly turns off the MOSFET to block the discharge path from Cin to the system. After the main power path is completely disconnected, the interface is physically detached, and no current flows at this time > For insertion, long pins (typically for ground and control signals) make contact first…

The phrase "when it is detected" makes me nervous.

That's why I included the bottom part describing how some pins are longer than others. It's sort of how some hotplugs work in most cases. First ground connects, then other set of pins and so on. So when is detected a physical act of being disconnected.

Re: Data centers are transitioning from AC to DC

#416

Post by kmacdough »

brucedawson wrote: post #383
Animats wrote: post #118

800V to each rackmount unit, with hot plugging of rack units? That's scary. The usual setup at this voltage is that you throw a hulking big switch to cut the power, and that mechanically unlocks the cabinet. But that's not what these people have in mind. They want hot-plugging of individual rackmount units. GE has a paper about the power conversion design, but it doesn't mention the unit to rack electrical and mechan…

It's easy to make these 800V systems totally safe. You just have to combine this idea with the extremely sensible plan to put data centers in space and then there will be no worry about when "someone pulls out a rackmount unit" because there not be someone within hundreds of kilometers.

The concern isn't keeping people out of the facility altogether. It's keeping people safe when they are hot swapping dead or outdated rack units.

You could consider a robotized approach, but for now robots aren't very good at this type of task. Whether the robotized system is in space is irrelevant. It's not a "next five years" type of solution.

Re: Data centers are transitioning from AC to DC

#417

Post by kmacdough »

elif wrote: post #307
QuantumGood wrote: post #298

Earlier quoted context omitted.

I think you're being downvoted for speaking of a complex future possibility ("robots and intelligent machines ... solution") as if it was a proven commodity. There will be many twists and turns in the path to the possible reliability, scalability, and cost effectiveness of robots and intelligent machines.

Yea I literally said long term but HN voters have such a hate boner for anything adjacent to AI

But the discussion is about the safety of systems being actively implemented. For now, people are required to maintain data centers. Right now, these centers are transitioning to high voltage DC. Right now the best attempts at fully automated data centers are in progress with unverified status. So, for now we need to keep the humans safe. Future data centers not needing humans doesn't keep the current humans safe. Thus, optimistic future speculation is off topic and not relevant to the discussion of human safety with high voltages.

People are tired of off topic speculation masquerading as relevant to real world problem solving. It's not a hate boner.

EDIT: expanded to make it clearer why I believe the speculation to be wildly off topic for this particular thread.

Re: Data centers are transitioning from AC to DC

#418

Post by jcalvinowens »

Dylan16807 wrote: post #414
jcalvinowens wrote: post #412

Earlier quoted context omitted.

> but you only get the safety benefit on three phase equipment. The wye ground is beneficial even if there are no three phase loads, because the line-ground voltage is 1/sqrt(3) and you can use cheaper switchgear. The 3-phase alternative to a wye ground is a corner ground (grounding a live phase of a delta secondary), which isn't done in modern installations because ground faults are full line-line voltage and you ne…

I'm not talking about the safety of different ways of doing three phase. I'm taking it as a given that three phase is wye ground and optimal for safety. My point is that in the context of a 230V single phase circuit, your ground is no longer in the middle. The ground is on one end of your single phase. If you want a safer single phase, you need to rebalance it to +115 and -115.

I thought they meant a "two phase" service where the two phases are 120 degrees out of phase instead of 180, like an apartment fed with two poles of a 208V wye with 120V to neutral/ground, which is balanced. If it's just a single phase, you're right.

Re: Data centers are transitioning from AC to DC

#419

Post by hinkley »

mikewarot wrote: post #360
hinkley wrote: post #319

Earlier quoted context omitted.

The power connectors will be on the far side of the rack from the service side so shouldn’t be a problem for humans touching the third rail so to speak. With that sort of voltage you should be able to use a capacitive or inductive sensor to activate a relay.

With a power rail that could supply kiloamps of fault current, thus megajoules of energy into an arc, I wouldn't be so sure of that. Copper vapor inhalation is a definite possibility and a horrible way to die.

Obviously the contact point in the sled will need to be disconnected while not grounded, as the top level suggested, or shorted to ground across a large resistor. It’s not the amperage that’s going to cause problems it’s the 800 volts, backed by the amperage. Small enough capacitance and large enough ground load should let you tap in without frying anything including air.

Wouldn’t the biggest problem will be loading sleds into a hot rack, with all of the sleds powered down? Which probably you shouldn’t do. The parallel loads on a rack that’s half on should sink a lot of the potential.

Re: Data centers are transitioning from AC to DC

#420

Post by Dylan16807 »

jcalvinowens wrote: post #418
Dylan16807 wrote: post #414

Earlier quoted context omitted.

I'm not talking about the safety of different ways of doing three phase. I'm taking it as a given that three phase is wye ground and optimal for safety. My point is that in the context of a 230V single phase circuit, your ground is no longer in the middle. The ground is on one end of your single phase. If you want a safer single phase, you need to rebalance it to +115 and -115.

I thought they meant a "two phase" service where the two phases are 120 degrees out of phase instead of 180, like an apartment fed with two poles of a 208V wye with 120V to neutral/ground, which is balanced. If it's just a single phase, you're right.

EU power is ~230V on a single phase and ~400V between phases. So a house usually gets three phases, but the only appliance where the voltage to ground is less than the total voltage is probably the oven.
Post reply on HN