Internet's Energy Needs Growing Faster Than Efficiency Gains

Electrons may not weigh anything, but it takes some heavy lifting, both literal and figurative, to point them in the right direction. Reader terrancem writes with this excerpt: "Energy efficiency gains are failing to keep pace with the Internet's rapid rate of expansion, says a new paper published in the journal Science. Noting that the world's data centers already consume 270 terawatt hours and Internet traffic volume is doubling every three years, Diego Reforgiato Recupero of the University of Catania argues for prioritizing energy efficiency in the design of devices, networks, data centers, and software development. Recupero highlights two approaches for improving efficiency: smart standby and dynamic frequency scaling or CPU throttling."

Comments

What?

[Anonymous Coward]

Electrons may not weigh anything

You lost me there.

Re:What?

[Fallingcow]

I knew those Higgs Boson experiments would lead to no good, but I didn't expect this!

Re:What?

[GodfatherofSoul]

You're not moving fast enough.

Re:What?

[Synerg1y]

Also... seeing as the world population isn't going to double every three years, how is internet traffic?

Another junk article.

Go speculate on lemmings and leave technology to the people who can actually conceptualize it.

Re:What?

[Githaron]

Because the general trend is the average person's usage has been going up over time. Netflix alone has substantially increased what the average person consumes.

Re:What?

[Synerg1y]

It might go up a bit... but 4x over 6 years... even 2x over 3 years... complete BS. Most people who are going to be using netflix in 3 years are already using it.

I agree with TFA title btw, not the summary. Traffic is increasing, and there hasn't been a whole lot of new stuff in the way of reducing server power consumption or cooling. Though there was that one DC that used a nearby water source to cool itself... nobody's gonna pack up their DC's foundation and move to the ocean side.

In fact, I doubt this is anything anybody needs to worry about as the consumption increases very slowly and the current energy grid is equipped to provide.

Re:What?

[noh8rz10]

It might go up a bit... but 4x over 6 years... even 2x over 3 years... complete BS. Most people who are going to be using netflix in 3 years are already using it.

hint: netflix for pr0n.

Re:What?

[Githaron]

Eventually, media streaming sites are going to start offering higher quality streams than they do now. More people are buying 3D-capable TVs/screens. Many of those people will start expecting their media sites to start including 3D content. More and more media sales are being distributed digitally via downloads instead of disks. More and more people are moving to using VOIP and other internet based communication. Average users are starting to backup/sync to the cloud. Combining everything it is not hard to image "Internet traffic volume is doubling every three years" for at least a while.

Re:What?

[Hal_Porter]

Reading timothy's summaries these days is like watching an unhappy chimp in zoo throwing faeces at the visitors.

Re:What?

[voidphoenix]

Higher-quality video and audio. Higher resolution video and images. More dynamic web page elements, more flash, more scripts, more ads. More fscking 3rd-party tracking. More pr0n...

See: Parkinson's Law, general form: The demand upon a resource tends to expand to match the supply of the resource. It applies to storage, processing and transmission requirements.

Back when we used dial-up and n-Gigabyte drives, we'd download 128 kbps or worse audio, low-res images and really shitty video. With today's broadband and n-Terabyte storage, it's 1080p, lossless audio and multi-megapixel images. What does the future hold? More people on broadband, quad-HD, 24-bit-96 kHz audio and Gigapixel images, and maybe even simsense...

Re:What?

[Synerg1y]

As the younger generations eclipse the older generations the amount of users who can do those things will go up and more infrastructure will be required (servers, cables, etc...)... but that's a decades thing, not a 3 year thing. At present, a ton of people have regular cable with netflix or w/o and still use that primarily. A ton of people still have tvs that aren't flat panels and most people don't want to pay monthly to back up their data (that hopefully will never change).

I agree that eventually it'll double, but nowhere near what's being mentioned in the article marking the article as completely BS.

Is that per hour ?

[Anonymous Coward]

270 terawatt hours! Is that per hour I wonder ?

Re:Is that per hour ?

[noh8rz10]

it's probably per year. don't you think? doubtful that they consume 270 TW of power.

Re:Is that per hour ?

[AlphaWolf_HK]

By my calculation, that is 223,000 bolts of lightning. Great scott!

Re: Electrons may not weigh anything

[paradigm82]

Actually, the mass of an electron is: 9.10938291(40)×1031 kg :-)

What about the Energy offset?

[NFN_NLN]

What about the energy offset?

How much energy is consumed by driving to blockbuster, picking up a physical tape that had to be produced and shipped to the store Vs. streaming from Netflix?
How about paying bills online vs mailing an envelope.

I'm not sure what the number is but it may be possible that for every increase in energy 'x' by computers there was '5x' amount of energy saved in other areas???

Re:What about the Energy offset?

[mellon]

If you're going to go there, it's probably worth noting that one really big consumer of CPU cycles online is encryption. This isn't a big deal for regular stuff, but when you're encrypting a 4Gbyte video stream, that's a big deal. IOW, DRM is the next new carbon polluter...

Re:What about the Energy offset?

[DrStrangluv]

This is definitely happening. It is a factor, and an important one. But let's not forget our Economics. Economics claims that the world's appetite for energy has some level of equilibrium to it, such that as energy is saved from one area (such transporting rental DVDs or bill envelopes) it's likely picked up by another area... and it's almost impossible to spot the corresponding increase.

The same effect applies to nearly every effort so far at reducing carbon emissions. There are lots of things aimed at specific places like cars or power plants, but not enough yet to actually change appetite, and truly alter the equilibrium state.

Re:What about the Energy offset?

[Entropius]

Is it CPU cycles that take the power?

Suppose I stream a DRM'd movie from Netflix that's 4GB. I don't know how to measure it explicitly on my computer, but I know I can do the decode entirely in software, and that the TDP of my CPU is 35 watts. I doubt that the difference between playing the movie with and without encryption is that big of a fraction of that -- perhaps 5W?

How does that compare to the power used by the routers etc. that carried that data to me?

Re:What about the Energy offset?

[Maximum Prophet]

Is it CPU cycles that take the power?

Suppose I stream a DRM'd movie from Netflix that's 4GB. I don't know how to measure it explicitly on my computer, but I know I can do the decode entirely in software, and that the TDP of my CPU is 35 watts. I doubt that the difference between playing the movie with and without encryption is that big of a fraction of that -- perhaps 5W?

How does that compare to the power used by the routers etc. that carried that data to me?

Good question, but unencrypted data caches better. If you and your neighbors all want to watch the same show, a torrent-type protocol that sends a bit of the show to each, then your computers trade amongst themselves, is much more efficient that sending a specific stream to each machine.

Re:What about the Energy offset?

[lgw]

What about the energy offset?

What about just generating more power? Power for transportation is a bitch, since it still mostly comes from oil, but electrical power isn't so problematic.

Natural gas is nearly free right now, and burns quite clean. Solar is emerging, and in another 20 years will likely be viable at industrial scale. In the US we're way behind on our power distribution networks, but there's no technological hurdle there, it's just us being cheap about infrastructure (and large centralized power consumers are by far the easiest to build new capacity for). There's just no real reason to worry about electrical power consumed industrially.

Re:What about the Energy offset?

[skids]

Encryption algorithms are one of the few areas where software developers pay close attention to efficiency in both software and hardware implementations, because they need to run on embedded devices with extremely constrained power and computational resources.

However, with everything moving to dynamic languages running on VMs that can come up with things to do with "spare" CPU cycles, like thumb through their garbage collection area, re-JIT codepaths, and recalculate heuristics, we're probably headed in the wrong direction in the software area overall when it comes to power efficiency -- especially since the rationale for using these types of languages is primarily to cut development time and in that setting, asking developers to put in performance/economy hints will get the cold shoulder. Meanwhile rapid prototyping means everyone is perfectly happy to reinvent wheels, since it has become so very easy to do so.

Re:What about the Energy offset?

[ColdWetDog]

Natural gas is nearly free right now, and burns quite clean.

Wait. What? Free exactly where? It's low cost compared to some other energy products, but hardly free. It's a PITA to move around and store.

And clean is relative ... (from the Wikipedia article)

Natural gas is often described as the cleanest fossil fuel, producing less carbon dioxide per joule delivered than either coal or oil[32] and far fewer pollutants than other hydrocarbon fuels[citation needed]. However, in absolute terms, it comprises a substantial percentage of human carbon emissions, and this contribution is projected to grow. According to the IPCC Fourth Assessment Report (Working Group III Report, chapter 4), in 2004, natural gas produced about 5.3 billion tons a year of CO2 emissions, while coal and oil produced 10.6 and 10.2 billion tons respectively (figure 4.4). According to an updated version of the SRES B2 emissions scenario by 2030 natural gas would be the source of 11 billion tons a year, with coal and oil now 8.4 and 17.2 billion respectively because demand is increasing 1.9 percent a year.[53] (Total global emissions for 2004 were estimated at over 27,200 million tons.)

In addition, natural gas itself is a greenhouse gas more potent than carbon dioxide. Although natural gas is released into the atmosphere in much smaller quantities, methane is oxidized in the atmosphere into CO2, and hence natural gas affects the atmosphere for approximately 12 years, compared to CO2, which is already oxidized, and has effect for 100 to 500 years. Natural gas is composed mainly of methane, which has a radiative forcing twenty times greater than carbon dioxide. Based on such composition, a ton of methane in the atmosphere traps as much radiation as 20 tons of carbon dioxide; however, it remains in the atmosphere for 8–40 times less time. Carbon dioxide still receives the lion's share of attention concerning greenhouse gases because it is released in much larger amounts. Still, it is inevitable when natural gas is used on a large scale that some of it will leak into the atmosphere. (Coal methane not captured by coal bed methane extraction techniques is simply lost into the atmosphere. Current estimates by the EPA place global emissions of methane at 3 trillion cubic feet (85 km3) annually,[54] or 3.2 per cent of global production.[55] Direct emissions of methane represented 14.3 per cent of all global anthropogenic greenhouse gas emissions in 2004.[56]

Solar is emerging, and in another 20 years will likely be viable at industrial scale.

It's already here but it's only cost comparative to $100 / barrel oil. Apple and Google have datacenters that are predominantly solar powered, but it's still expensive. Certainly a better way to go than fossil fuels.

In the US we're way behind on our power distribution networks, but there's no technological hurdle there, it's just us being cheap about infrastructure (and large centralized power consumers are by far the easiest to build new capacity for). There's just no real reason to worry about electrical power consumed industrially.

I just love statements like this. "There is no reason (other than reality) than we can't do x". There is plenty of hurdles involved in bringing our energy distribution up to speed. Just because it's not a matter of technology doesn't make the problem go away. Politics and economics are very, very powerful forces in our society.

Re:What about the Energy offset?

[lgw]

Wait. What? Free exactly where? It's low cost compared to some other energy products, but hardly free. It's a PITA to move around and store.

Wow, I see /. is still the home of OCD literalism and obliviousness to hyperbole. How about: natural gas is currently amazingly cheap and plentiful by historical norms, and fuel cost isn't the limiting factor in generating more power right now.

It's already here but it's only cost comparative to $100 / barrel oil. Apple and Google have datacenters that are predominantly solar powered, but it's still expensive. Certainly a better way to go than fossil fuels.

Not this year. Solar is getting better, but has a ways to go before it's cheaper long-term than natural gas at today's prices. It's just a matter of time for solar, of course, but it's still mostly hype.

There is plenty of hurdles involved in bringing our energy distribution up to speed.

Sure, but it's not some hypothetical breakthrough like fusion. But for industrial generation, you can just build the power plant next door: lots of heavy industry does this, and it may well be the future of datacenters (or, like today, you just build datacenters next to the power plants instead).

Re:What about the Energy offset?

[mellon]

"The internet" includes the content-delivery networks, which re-encrypt the DRM'd media for each person who consumes it. Also, be aware that 35 watts times a million users is 35 megawatts. For a billion users, that's 35 gigawatts; more than enough to power a flux capacitor to get Marty McFly back to the future...

Re:What about the Energy offset?

[mellon]

Yup. Encryption algorithms are very efficient; that's why you can stream data through your ssh connection at the full bandwidth of your link. But very efficient isn't the same thing as free, and when the volume of data being encrypted is large, the power consumption starts to add up. Most of the encryption you do for privacy, as long as you aren't watching kiddie porn over TOR, is peanuts compared to the cost of encrypting a video stream.

Re:What about the Energy offset?

[evilviper]

one really big consumer of CPU cycles online is encryption

No. On modern computers, encryption is insignificant. A single core, 2GHz Pentium M CPU would need less than 1 minute of CPU time to AES encrypt/decrypt your 4GB, 100+ minute video stream (working out to a nice round 1%). And if your CPU is newer, it might even be offloaded to the AES-NI instruction set, making it more than an order of magnitude faster still.

Re:What about the Energy offset?

[mellon]

Or, it might be done by your JVM or in Javascript. It really varies a lot. But hopefully you are right, and at least on the server side they are using AES hardware.

Re:What about the Energy offset?

[gbjbaanb]

absolutely. I wish the time spent inventing Java and .NET had been spent making libraries and patterns that improved the existing efficient language.

I doubt anyone will change it, but it needs to be continually re-emphasised. Its not just saving the planet, but saving your electricity bill that matters. We all need to be evangelists on scrapping the in-efficient software. Microsoft had a little push towards this with their C++ renaissance but I think its fizzled out when Sinofsky left.

Re:What about the Energy offset?

[CAIMLAS]

Most CPUs have hardware exensions for eg. AES these days. It's easy to offload that and, often, it makes sense to have a single point at the edge of the network where that's all done (if your backend servers are numerous enough). I wouldn't be surprised if some of the DRM methods got put into silicon sooner than later...

That said, my experience has been that the biggest 'waste' of CPU cycles (and general performance) has been Indian developers who are not held responsible for their excessive use (aka abuse) of hardware. You need HOW MUCH RAM for that?! I'm sorry, I know you're writing in Java/.NET/whatever, but multiple hosts with 32GB of RAM getting maxed out by your java apps is not reasonable.

I'm being exceptionally harsh to Indian devs, because I've only seen them get away with it. Seems everyone else cares about the hardware cost, but it's only Indian developers who's development hours are more valuable than the hardware costs... maybe they're graded on quality based on number of buffer overruns and gigs of RAM used?

Re:What about the Energy offset?

[CAIMLAS]

This is largely inconsequential. Netflix, Prime, et al have been dropping storage systems into ISP datacenters for years. The ISP benefits because their upstream pipe is less saturated (they only need to keep their local topography 'fast', which costs a lot less) and the content provider benefits because they don't have to pay for the bandwidth to push the content to the customer at all anymore. This is how eg. Akamai operates.

Will this effect our ability to stream porn in 4k?

[Anonymous Coward]

I'm not goin back to layin in the back yard and waiting for a boob shaped cloud to float by....

270 terrawatt hours

[Zcar]

In how long?

Could be 30 gigawatts for a year, 300 megawatts for a decade, 370 gigawatts for a month or even 16.2 petawatts in a minute.

Units matter!

Re:270 terrawatt hours

[gman003]

I believe it was implied that this was per annum (270 TW-h/year).

If Wolfram Alpha is correct, that comes out to 31GW, which it notes is about 1/75th the world's power consumption. This seems relatively reasonable, more so than if you interpret it as per-month (16% the world's power) or per-decade (roughly the power of the Hoover Dam).

Still very confusing, though. Bad science.

Re:270 terrawatt hours

[Chris Mattern]

Which of course, raises the question, why couldn't you just bloody SAY "31 Gigawatts" instead of tangling yourself in this foofaral of extraneous time units that you didn't even get right?

Re:270 terrawatt hours

[wjwlsn]

31 GW is still pretty damn high... that's like 31 average-sized nuclear power plants dedicated 100% to running the internet... or like 25 simultaneous lightning strikes to get a fraction of a second of porn.

I interpreted that sentence to mean 270 TWh over the 3 years it takes to double internet traffic (according to the article). That's still a little over 10 GW.

Re:270 terrawatt hours

[Chris Mattern]

Which of course, raises the question, why couldn't you just bloody SAY "31 Gigawatts" instead of tangling yourself in this foofaraw of extraneous time units that you didn't even get right?

Re:270 terrawatt hours

[Anonymous Coward]

The 1/75th figure appears to be way too high.

According to Wikipedia, annual world energy consumption was 143,851 TWH in 2008.

If the entire Internet runs on 270 TWH annually...it is likely far more energy efficient than the activities/alternatives it displaced.

Re:270 terrawatt hours

[Zcar]

Energy consumption, or electrical energy consumption? Total energy consumption is greater than electrical energy consumption by a pretty big factor (fuel for vehicles, natural gas for heating/cooking, etc.). Wolfram reports annual world electrical consumption of about 20230 TWh or 2.3 TW, which gives about 1/75th.

Re:270 terrawatt hours

[bryan1945]

I only except measurements in Planck time units.
I don't even know if that makes sense in this discussion. I've just been itching to use "Planck time" somehow for a bit.

Also getting rid of HTTP + HTML.

[master_p]

We need a binary protocol and tools to handle that binary protocol.

Yeah, I know, text is ubiquitous, but so this new protocol will be if it is open source.

But a binary protocol will reduce consumption by a large amount.

Re:Also getting rid of HTTP + HTML.

[jjeffries]

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

Re:Also getting rid of HTTP + HTML.

[tibit]

So, realistically, do we know how much HTTP traffic is compressed? Do we know if the gzip compression used is anywhere nearly as good as a dedicated compressing encoding could be? How energy efficient is running all this data through zlib vs. code that knows what it is encoding?

Re:Also getting rid of HTTP + HTML.

[gbjbaanb]

it'll reduce CPU processing requirements by a relatively small amount. One place I worked, we had a XML protocol for storing our data, replacing it with a binary one increased performance by 20%. Now that's not to be sniffed at, but it isn't a panacea.

What we can do however, is get rid of the script language based web sites. I know there's a low entry barrier when using them, but every site that needs performance ends up writing it in a compiled language, and then C/C++ if they've got sense (Java, and .NET are better, but still not good enough for this problem).

Now if we had all server computing based on an efficient language, we'd see energy consumption reduced by quite a bit.The super computers we have nowadays could run a great many sites instead of just a handful. And yes, they'd also use a binary protocol by default instead of the XML based stuff almost every "easy to use" system and framework uses.

Re:Seriously!

[noh8rz10]

Set up an international enforcement body. I am 100% serious.

fascist.

Details

[tech.kyle]

Recupero highlights two approaches for improving efficiency: smart standby and dynamic frequency scaling or CPU throttling.

Turning a 1 hour task at 100 watts in to a 2 hour task at 75 watts isn't efficient.

why not just buy carbon credits?

[alen]

and plant some trees? then it evens out

Re:why not just buy carbon credits?

[Shakrai]

Not when the trees die and release virtually all of that carbon back into the atmosphere as they decompose.

Re:why not just buy carbon credits?

[turbidostato]

"Not when the trees die and release virtually all of that carbon back into the atmosphere as they decompose."

Bury them. And you gain the nice side effect that it'll replenish our oil reserves in mere hundreds millions years.

Re:why not just buy carbon credits?

[Shakrai]

What do you bury them with? Fossil fuel powered construction equipment? That's a bit like driving 10 miles to the recycling center with a six pack of soda cans because you don't have curb side pickup. ;)

Mobile devices

[Dan East]

On the other hand, more and more content is being consumed by mobile devices, which are vastly more energy efficient than desktop computers. Even desktop computers are more efficient than 10 years ago, primarily due to the complete abandonment of power hungry CRT monitors. So the good news is the part that's hard to control, which is the diverse and eclectic individuals who consume the content, are already many times more energy efficient than they were 10-15 years ago.

just switch to SSD for all storage

[alen]

hard drives suck up the most power
i'm sure the government can make up a tax credit to get people to buy up SSD's

Re:just switch to SSD for all storage

[Entropius]

Funny, people seem to be buying the things just fine without artificial market distortions.

And hard drives don't take that much power...

Best Author/Title correlation ever.

[Anonymous Coward]

Did anyone notice the meaning in Italian of the paper author's last name is "re-forged recycling"?

Re:Best Author/Title correlation ever.

[dasbub1576]

I was ready to call bullshit on the whole story when I saw the name. Non parlo italiano, but "recupero" in an efficiency story stands out.

Computing is efficient

[Hentes]

Computing is orders of magnitude more efficient efficient than the traditional ways it replaces.

Re:Who cares?

[CanHasDIY]

Usually when people use stuff, that involves resources.

And resources are finite. Hence the need for greater efficiency.

I think you may be in the wrong place - posts of mindless drivel, free of cogent thought belong to Yahoo, not Slashdot.

Re:Seriously!

[Anonymous Coward]

Your post advocates a

( ) technical (X) legislative ( ) market-based ( ) vigilante ( ) form-based

approach to fighting spam. Your idea will not work ...

Yada yada yada ...

(X) No one will be able to find the guy or collect the money^W^Whis head

Yada yada ...
(X) Lack of centrally controlling authority for email
(X) Open relays in foreign countries
(X) Asshats
(X) Jurisdictional problems
(X) Armies of worm riddled broadband-connected Windows boxes
(X) Extreme profitability of spam
(X) Technically illiterate politicians
(X) Extreme stupidity on the part of people who do business with spammers
(X) Dishonesty on the part of spammers themselves
(X) Bandwidth costs that are unaffected by client filtering

Yada Yada

(X) I don't want the government reading my email
(X) Killing them that way is not slow and painful enough

Furthermore, this is what I think about you:

(X) Sorry dude, but I don't think it would work.
(X) This is a stupid idea, and you're a stupid person for suggesting it.
( ) Nice try, assh0le! I'm going to find out where you live and burn your house down

Re: Electrons may not weigh anything

[i kan reed]

Actually, the mass of an electron is: 9.10938291(40)×10^31 kg :-)

I think you might have missed a minus sign there. Unless the Sun is an electron.

Re: Electrons may not weigh anything

[ByOhTek]

Damn. I want to know what universe you live, in, those electrons are HEAVY.

The sun only weighs ~1.9891x10^30kg, an electron is almost 5.0 x 10^1000 times heavier!
( http://en.wikipedia.org/wiki/The_Sun )

Re:Seriously!

[i kan reed]

fascist.

Think a lot of people would have been more OK with Hitler if he were gassing spammers and not Jews.

Better editors, anyone...

[skeptikal]

>>> Electrons may not weigh anything, but it takes some heavy lifting...

Year-on-year the editing gets worse and worse.

What are we, 5-th graders?

Re:Better editors, anyone...

[dasbub1576]

Oh I don't know about that. /. editing has been consistently pisspoor through the years. I'm just glad that the Roland Piquepaille years are behind us.

Electrons have mass

[Maritz]

They're not photons or neutrinos. So yeah they do weigh something. If I was writing a submission summary I'd check that kind of statement in case I end up looking like (more of a) gimp. ;)

Re:Electrons have mass

[Entropius]

Neutrinos have mass too; this was discovered by the fact that they oscillate from one flavor eigenstate to another.

This is sort of like the way Catholics have mass; they have a cracker that oscillates from bread to jesus, showing that the eigenstates of flavor aren't stationary states of the Hamiltonian...

Re:Electrons have mass

[Maritz]

Heheh yeah. I've heard the consensus lately is that neutrinos have a very small but probably non-zero rest mass.

Internet is energy ineffcient which..

[houbou]

.. makes sense, after all, there was no consideration about the actual power requirements, the Internet has been work in progress since its inception. It has grown, but it's never been looked at as a whole in terms of hardware. But to make it energy efficient in a purist sense, there would have to be enforced standards on hardware requirements which would entail ISPs to reevaluate and tweak their setups. This won't be cheap, but I'm sure it will still be cost-effective compared to business as usual.

Re:Internet is energy ineffcient which..

[Entropius]

still be cost-effective compared to business as usual.

If it were cost-effective, wouldn't businesses have already done it?

The problem is that power is artificially cheap; the price of the damage done by carbon emissions is not included in the price of burning coal. Seen this way, a carbon tax isn't an artificial meddling in the market; it's the removal of the subsidy that people burning carbon enjoy right now, in that they can cause environmental damage without bearing the cost (or, if you like, consume part of a limited resource without having to pay fair market value for it, where that limit is the sustainable level of emissions).

Remove that, and you won't have to impose efficiency from above; people will do it naturally, as a way of saving money.

Re:Internet is energy ineffcient which..

[dasbub1576]

Every sentence in your post should be wrapped in "citation needed". What constitutes "The Internet" in this discussion? By what metric is it inefficient? What is the basis for your claim that there was no consideration about the actual power requirements? What do you mean by "energy efficient in a purist sense"?

Re:Internet is energy ineffcient which..

[Ambassador Kosh]

For some reason many people see externalizing costs as completely okay and not a subsidy but if you suggest taking away the ability to externalize costs that is seen as a tax.

I often wonder how cheap coal would be if the full costs had to be paid for using it instead of the taxpayer and others being stuck with the environmental, medical etc bills. Is natural gas really a cheap power source? If they had to pay the full cost of the environmental damage they are doing how cheap would it be?

I do know that natural gas fracking could be done safely but it would also be more expensive than it is now and companies are cutting too many corners. Would natural gas fracking still be a good source of natural gas if it had to be done safely?

If a company makes 1 million in profit but costs the society 2 million in medical and environmental issues that is a loss for the society not a profit and we need to realize that.

Re:Internet is energy ineffcient which..

[khallow]

For some reason many people see externalizing costs as completely okay and not a subsidy but if you suggest taking away the ability to externalize costs that is seen as a tax.

While I grant that it is possible to have a externality as a subsidy (for example, the nuclear industry's relative protection to liability from accidents), most externalities are not subsidies.

Further, many common approaches to "taking away the ability to externalize costs", such as pollution taxes, for example, are taxes.

I do know that natural gas fracking could be done safely but it would also be more expensive than it is now and companies are cutting too many corners. Would natural gas fracking still be a good source of natural gas if it had to be done safely?

I see no evidence to back your claim that fracking collectively isn't done safely. I'm sure someone out there is doing something unsafe or polluting. But that's why we have regulators and laws.

Re:Internet is energy ineffcient which..

[khallow]

It has grown, but it's never been looked at as a whole in terms of hardware.

Why should it ever be someone's job to do that, at least with respect to energy efficiency? I can see the boon to human knowledge to have people study the extent and impact of the internet.

But there's no genuine energy efficiency problem here. If there was, then everyone would be working harder on reducing energy consumption than on expanding their infrastructure. As it turns out, energy is dirt cheap, while the value from the internet is considerable. So I think the right balance is struck here with little to no interest in energy efficiency because there's little to no value to doing so.

Re:Internet is energy ineffcient which..

[Ambassador Kosh]

If you allow someone to pollute without charging them for it and the EPA, health insurance etc picks up the cost that is a subsidy to that industry. Removing that subsidy is not suddenly a tax.

I have read a fair number of reports on natural gas fracking sites that did not put the concrete liners in correctly (not far enough down, insufficient thickness etc) and there are so many of them they are not being inspected often enough. This allows companies to get away with many practices. This is a defacto subsidy for that industry since they are not paying the full costs of their activities. Other people are having to picks up those costs.

I don't know if the industry would still be profitable or not without exemptions from things like the clean water act but industries should not be able to externalize their costs. I also feel the same way about solar panels and the toxic chemicals that it takes to make some of them. If those toxic chemicals are being dumped without the company paying the full cost of dealing with the damage caused that is also a subsidy and should be removed.

All these externalized costs and subsidies are massively distorting how things are done. It is favoring certain technologies over others while we all pay the price.

The nuclear industry should also not have protection from accidents. The coal industry should not be able to legally pollute the air the way they do (with particulates, gases, damage in extracting coal etc) without paying for it either. I am not for ending only certain of these subsidies. I want to eliminate nearly all of them (except ones subsidizing things like healthy food, insurance etc for the poor).

Re:Internet is energy ineffcient which..

[khallow]

If you allow someone to pollute without charging them for it and the EPA, health insurance etc picks up the cost that is a subsidy to that industry.

No, it's an externality, a cost imposed on a third party. Which is why it's called that. A subsidy is a payment or transfer of something of value usually to assist in a given activity.

If the EPA deliberately paid for the harm caused by a business's pollution so that the business wouldn't have to pay for the externality itself (something the EPA doesn't do, BTW), then that could be a subsidy which also happens to be an externality.

I have read a fair number of reports on natural gas fracking sites

There's a lot of environmentalism oriented propaganda out there. I'm sure there is some truth to the claims of pollution and regulatory misconduct in there somewhere, but we need to keep in mind that fracking as well as any other major fossil fuel-based innovation is a huge threat to those who wish to end the use of fossil fuels (or even industrial society itself). And a lot of those people are willing to lie outrageously to get what they want.

My view is that oil drilling has gone on for a long time. Even fracking as a technique has been used for decades. If there was a serious pollution problem with this stuff we would have seen it long ago with major air and water quality problems nowhere near an oil well.

Re:Internet is energy ineffcient which..

[Ambassador Kosh]

It is my understanding that during various major oil spills the companies involved did not have to pay the total costs of the damages incurred and most of the tab was picked up by taxpayers. That kind of thing should not be happening. Oil spills will happen ,they should be part of the cost of doing businesses and insurance should be held for them or money saved to cover them.

It is not right that the public picks up the tab for business practices that cost us all severely. It should also not be possible to just declare bankruptcy instead of being able to pay the cost of the damage done. You should have to carry insurance for likely amounts of damage your company can incur so the public is not left holding the bill if you do something that causes a lot of damage. Otherwise you just encourage the behavior.

I wonder what technologies we would most likely be using right now and how quickly they would progress and how much effort would be put into making them better without so many businesses able to keep using their current business models and passing the costs onto the public. I wonder what the menu at McDonalds would look like, what would be the most common food in the supermarket, what kinds of transportation would we use etc.

Re:Internet is energy ineffcient which..

[khallow]

It is my understanding that during various major oil spills the companies involved did not have to pay the total costs of the damages incurred and most of the tab was picked up by taxpayers.

So what? That's not an actual externality since it's a cost voluntarily created by the respective government agency. Those tend to be wildly inflated costs. It's like blaming the entire cost of the US military-industrial complex on oil companies.

It should also not be possible to just declare bankruptcy instead of being able to pay the cost of the damage done.

Bankruptcy happens when the money's just not there. Unless you're going to give them the money to pay for damages, they're not going to pay for damages either way.

I wonder what technologies we would most likely be using right now and how quickly they would progress and how much effort would be put into making them better without so many businesses able to keep using their current business models and passing the costs onto the public.

You're probably looking at them right now.

So let me translate this...

[Lawrence_Bird]

Internet pron is causing global warming, m'ok? Save the environment, buy print editions of Playboy, Penthouse and Hustler.. or whatever else gets you off.

1.21 gigawatts

[wjwlsn]

hours in 3 years: 3*365.25*24 = 26298 h
average power over that period: 270 TWh / 26298 h = 10267 MW

So... like 8 simultaneous lightning bolts to run the internet for a fraction of a second?

Make internet privacy an environmental issue.

[big_e_1977]

Government monitoring and storage of all communications of its citizenry has got to have a tremendous carbon footprint. As does all the extra electricity used by Facebook, Google, Double Click et all to track my every move on the internet. How much energy could be saved by simply serving web requests, and not data mining it for government and corporate interests?

Re:Make internet privacy an environmental issue.

[dasbub1576]

Oh, okay. THAT's the problem. Data mining for government and corporate interests. What the hell does "simply serving web requests" mean? I don't even know where to start with this.

Re:Make internet privacy an environmental issue.

[dasbub1576]

"doing something" does not mean "doing something effectively", nor does it demonstrate any energy savings. A "web request" is an ambiguous term. Does it mean HTML requests only? Okay, what does that mean? Images, text, video? RequestPolicy would let you tailor it to your own needs, I'm just pointing out that the OP's suggestion is meaningless.

Re:Seriously!

[noh8rz10]

First they came for the spammers, and I didn't speak out because I wasn't a spammer...

Re:Who cares?

[Entropius]

Resources aren't all that finite. Right now, what's the problem with using power? Carbon emissions. But there are lots of ways to make power that don't involve carbon-based fuels; we just need to do them.

I wonder how much is Java and XML to blame...

[tibit]

I wonder how much does impact does Java and enterprisy XML-based web services have in all that. XML is a cache hog and memory bandwidth hog, never mind a network bandwidth hog. Java has huge runtime costs of abstractions needed for good software design. I think it's time to come up with something where the abstractions' cost is pushed to compile time. You know, something that has been solved long ago in the form of LISP code-generating macros. Sigh.

Re:I wonder how much is Java and XML to blame...

[SplashMyBandit]

If your software doesn't have to work or provide utility to human society then you can make it take zero resources and run in zero time. Now it turns out that Java is *very* fast. It turns out that Java's abstractions are up to the developer. N00bs, and those on the lecture circuit, add way to much abstractions. I add the right amount. *one layer of indirection for parts that may be extended*. That is all that is needed.

Furthermore, through use of Java and XML you can rapidly built systems through massive re-use (and nifty stuff like JAXB which takes much of the pain of using XML away). This allows equally massive *savings* in energy through vastly reduced development time.

You know, something that has been solved long ago in the form of LISP code-generating macros. Sigh.

LISP is a nice language. Good luck getting everyone to use it. Other languages were invented for a reason, they were easier for teams of non-fanbois to be productive and get real shit done. Deal with it (please).

So, nice try at grinding your pro-LISP axe. But a bit of a fail considering the holistic situation (both in terms of energy use and software development reality).

Re:Seriously!

[PhamNguyen]

Yes there will have to be sacrifices, but it's for the greater good. We can get back to principles like proportionate punishment once the evil of spam is thoroughly purged.

Re:Seriously!

[tibit]

This is one of the most informative comments to this article. That's a reason both to celebrate and to lament :/

Efficiency is nice

[fustakrakich]

But I prefer robust, something that can tolerate the occasional anchor drop, route around censorship, and protect anonymity.

Re:Who cares?

[PhamNguyen]

I don't know if this is AC's point, but the fact that we need more efficience across the board, does not imply that everything needs to be done more efficiently.

E.g. the money that an NGO or a company looking to become "green" spends on making its data centres more efficient, might be better spent making its transportation more efficient, etc.

Until we have a global carbon tax, advocacy should focus on finding the "easy" efficiency gains, or conversely, companies or sectors performing less efficiently than is known to be technically possible.

Simply saying "everything must be made more efficient" is wrong, and inefficient.

Stop collecting all that data, then!

[genericmk]

If governments and corporations would just stop collecting all that data on everyone...

Re:Seriously!

[Githaron]

What's your IP address?

Re:Seriously!

[dasbub1576]

Welcome to /.

Re:Angular Momentum

[Entropius]

Per the Daily Mail, that great bastion of scientific rigor, we find that the internet has a mass of about 50 grams, "the same as a strawberry":

http://www.dailymail.co.uk/sciencetech/article-2057018/Internet-weighs-strawberry.html

Then the angular momentum of the internet about the center of the Earth is (50 grams) / (24 hours) * R, where R is the mean radius of the internet from the axis of rotation of the Earth. Computing R is hard, since the parts of the internet in Europe (far northern latitudes) will contribute less than those near the equator. If we take R_earth cos 45 as an estimate for the radius (which is probably sensible, roughly splitting the difference between Europe and the US/Japan/Korea), we get that the angular momentum of the Earth is

2.6 kilogram-meters per second.

Re:Who cares?

[ColdWetDog]

Resources aren't all that finite. Right now, what's the problem with using power? Carbon emissions. But there are lots of ways to make power that don't involve carbon-based fuels; we just need to do them.

When you're Ruler of the Planet you can probably get that done. Dealing with real politics is such a drag.

Re:Who cares?

[Zontar The Mindless]

...posts of mindless drivel, free of cogent thought belong to Yahoo, not Slashdot.

Hi! You must be new here...

Re: Electrons may not weigh anything

[Anonymous Coward]

Is that what the sun weighs on earth or the moon?

How much energy is saved

[EmagGeek]

By not having to mail letters, package software in retail packaging and ship to a store or end user, travel to other office locations for meetings, and other spendy endeavors?

Overall the Internet is a huge energy saver.

Re:Seriously!

[Anonymous Coward]

127.0.0.1

The Jevons Paradox

[Mister Liberty]

... ensures we're all doomed anyway.
Yeah!

power != energy

[Shakrai]

Which of course, raises the question, why couldn't you just bloody SAY "31 Gigawatts" instead of tangling yourself in this foofaral of extraneous time units that you didn't even get right?

The watt is a measurement of power. The kilowatt-hour is a measurement of energy. 31 Gigawatts on its own is meaningless. That incandescent light bulb in your closet is rated for 100 watts, does that tell you how much it cost you to operate last month? The power consumption is useless without knowing how long the device was turned on, and it's easier to say "That light bulb consumed 15kWh last month" than to say "That 100 watt light bulb was turned on for 150 hours last month."

Re:power != energy

[Anonymous Coward]

31 Gigawatts on its own is meaningless. That incandescent light bulb in your closet is rated for 100 watts, does that tell you how much it cost you to operate last month? The power consumption is useless without knowing how long the device was turned on,

Try turned on forever. In fact, 31 GW is the current average power consumption, which will likely increase over time.

On the other hand, I live in a place (Finland), where heating is needed for most months of the year (it's -7C at the moment here in Espoo). For anybody living here, much of the computer power is free. In other words, if we weren't running computers, we'd be wasting the same wattage in radiators. The heating efficiency of a computer is 100%.

Re:power != energy

[expatriot]

Of course using a computer as an electric heater is less efficient than a dedicated electric powered exchange pump which can have effective efficiencies many times 100%

Re:power != energy

[Ginger Unicorn]

Given that the internet is never switched off, saying how much power it dissipates is just as informative and more concise than saying how much energy it consumed and over what period of time.

Wasted Energy

[CanadianMacFan]

I wonder how much of the energy being used in data centres is being wasted. And not just as in heat. I worked in one centre and we had one rack of blade servers that wasn't being used for anything but was constantly being left on. I would turn them off and next time I looked they would be turned on again. And they put out a lot of heat into the room. We had another two full racks of blades from another provider that were in constant use and they put out less heat than the one rack sitting idle.

Hopefully that has been changed there but I'm sure that it isn't the only place in which there are unused servers sitting turned on and left to idle 24/7.

16 Ways to Save the Planet #8

[wanfuse123]

I just finished writing an article on 16 ways to save the planet. Number 8 was to institute a efficiency standards. Design a moving goal post to keep pressing the issue in a sort of energy efficiency Mores Law. Currently our brains are a million times more efficient than the computers we run and at the same time are a million times more powerful! If we press the issue and put money into it we can build the technology to get our computers to match the efficiency of the human brain. There already has been several designs proposed to make this happen including using old analog types of computer designs instead of digital ones which are far more efficient for some things. Also designing chips to come up with correct answers using the chaos and noise rather than by overriding the noise by pushing high voltage differences between 1's and 0's.

Re:16 Ways to Save the Planet #8

[khallow]

What happens when our brains don't meet the efficiency standard? What do you propose then?

I might add that I find efficiency standards to be one of those dumb things that sounds smart at first. First, the obvious solution to efficiency is simply not to do it. Don't have a zillion people, don't have an internet, don't do anything that uses power, etc. Then you achieve perfect efficiency.

But the moment you decide that there's some things that we really need to be doing (say because those seven billion people aren't going away any time soon), then you are implicitly recognizing that there are more important things out there than efficiency.

Does the efficiency standard somehow take into account that some uses of energy are more important than conserving energy? Of course not. It's a standard applied blindly to everything. Hence, reason number one why it is a dumb idea.

Reason number two is that there simply isn't much value in conserving energy. Energy is dirt cheap. That indicates it is plentiful enough that we shouldn't care so much about how efficiently we use it.

Last, but not least, reason number three is closely related. As I noted, cheap energy means no real reason to conserve electricity. But in the case of expensive energy, everyone who pays for energy suddenly have huge incentives to conserve it. There still remains no reason to have a conservation standard, because everyone is working hard on conserving it.

Watt hours sound bigger for journalists

[Guspaz]

But perhaps a more sensible measurement is just to use the actual generating capacity required. 270 terawatt hours per year would be about 31 gigawatts. Consider that HydroQuebec alone produces more power than that from renewable sources, and suddenly it doesn't seem so big anymore.

I suspect that the Net saves energy.

[InterGuru]

I suspect that the Net saves energy. Someone using Netflix ( whose major energy consumption is from the TV, not the Internet) is not driving several miles to the theater. In the last few years miles driven per person has been decreasing, especially for the youngest drivers. Some of this comes from a bad economy, but some probably comes from substituting hanging out at Facebook, rather than a the mall.

A trip to the movies, say 20 miles, one gallon of gasoline in a typical car contains about 33KWH. By any measure this is much much greater than any concievable use for watching a flick at home. Add to that shopping online rather than driving to the mall, you have a net savings

I don't get the point

[khallow]

The internet has been growing exponential more or less for a couple of decades. Efficiency on the other hand can only do so well. You're not going to get exponentially improved efficiency (maybe in computing power, but not in cooling, manufacture, resource footprint of employees, etc). And efficiency is a trade off with actually doing stuff too. Try too hard to make something efficient and you will lose some degree of capability or action.

So of course, one would expect neither efficiency to be able to keep up with the growth of the internet nor for that criteria to be remotely useful to consider.

Power saving in a data center

[rlh100]

If you look at the actual article, it is about existing technologies that could allow data centers to save power. It talks about how smart standby and dynamic frequency scaling can be used to reduce the power consumption of servers.

For web sites with large server pools it would be interesting to scale the size of the load balancer pool and put excess servers into a low power standby mode.

I.e. Our server pool is 10X of what our average daily maximum network load is. This is because we get occasional traffic spikes due to [events|news stories|slashdot postings|etc] and we need to be able to scale quickly to handle the load. If we could shrink the server pool our load balancer uses to 2X and put the other 8X servers into a fast startup standby mode we would significantly reduce our daily power consumption. When the spike hit, we would put the 8X servers into full power mode and add them back to the load balancer pool. We would also put the servers into full power mode when we did software updates. This would keep all the servers current.

Approaches like this could potentially save significant power for a web site.

old gear

[porjo]

Another aspect of this is the old, inefficient legacy gear that could be decomissioned but isn't. Where I work there are literally dozens of old physical servers that could be virtualized. It's not being done, essentially due to mismanagement. I wouldn't be surprised if this pattern is being repeated many times over across the globe.

There should be an annual 'decomm a legacy server' day!

The energy consumption weights ...

[zzyzyx]

... assuming datacenters use 380V, just about
230TWh / 380V / (electron charge) * (electron mass) = 12.4 tons worth of electrons :-) (try typing the formula directly in Google!)

Re:Seriously!

[bryan1945]

You had me at
(X) Asshats

Re: Electrons may not weigh anything

[j-beda]

.....is almost 5.0 x 10^1000 times heavier!

ten to the thousand? Wow, that's a big number.

9x10^31 is not 1000 orders of magnitude greater than 2x10^30, it is only about 45 times bigger (assuming I haven't made another bone headed arithmetic error like everyone else in this thread trying to show off how much smarter each of us is than the last person.....)

feed the computers

[peawormsworth]

One day we will have large labour forces extracting energy for the sole purpose of feeding "the network" while governments let citizens starve and die out in the cold. And no one will find this strange. That is my darkest prediction for the future.

Re:Terawatt hours?

[lpq]

What units would you use?

We see batteries in amp-hours (@rated battery V)

Car batteries also in amp-hours at rated V

all of them put out energy amp*V for some amount of time...

amp*V=W W-hr is one of the most common units of power that most people are exposed to. So what would you use?

Re: Electrons may not weigh anything

[ByOhTek]

Actually I was just picking on the original poster for a typo.

He lost the "^" and the "-", and my brain was implicitly putting a "10^" in front of the 1031... Still a fail... but EVERYONE seems to be misreading everyone's post ... It's great!

Re: Electrons may not weigh anything

[j-beda]

Actually I was just picking on the original poster for a typo.

I knew you were razzing him about his error - but I guess you were to subtle for me (or perhaps more accurately I was too stupid for you). I thought you were just razzing him for forgetting the (-) in the exponent, whereas you were going for the difference between -31 and +1031 (and the +30 for the sun of course.)

I was feeling pretty good for a while when the AC said I was so smart, but I guess praise from an AC isn't worth much....