Catch up on stories from the past week (and beyond) at the Slashdot story archive

 


Forgot your password?
Close
typodupeerror
×
The Internet Science

'Slow' Light To Speed Up the Net 107

Posted by samzenpus from the haste-makes-waste dept.
JPawlak writes "Researchers believe that it may be possible to increase the speed of the Internet by slowing down certain parts of it by using metamaterials. Metamaterials could be used to replace the bulky and slow electronics that route Internet information, allowing for faster Internet speeds. As data nears its destination, the frequencies must be separated. The light must then be converted into electrical signals, which are stored, routed, and converted back into optical signals. The conversion not only adds significant cost and complexity to the process, but slows down the transmission as well. However, if the light signals could be slowed during the switching process, they would not need to be converted into an electrical signal. 'The ability to slow the light could be a tremendous force for telecoms that is sure to enhance speed and efficiency,' says University of California professor Xiang Zhang."
This discussion has been archived. No new comments can be posted.

'Slow' Light To Speed Up the Net More

'Slow' Light To Speed Up the Net

Comments Filter:

  • Hmmm (Score:2, Funny)

    by LightWing ( 1131011 )
    Am I the only one who thinks that sounds a bit paradoxical?

    • Re:Hmmm (Score:5, Interesting)

      by Serenissima ( 1210562 ) on Thursday August 14, 2008 @12:27AM (#24594743)
      Yup! It's similar to traffic congestion problem that someone figures out how to solve every couple months. If everyone's driving fast and there's a slow point, all the cars back up. If everyone, hell - if one person, slows down and leaves room inbetween their cars, that gives the tight spot enough room to accommodate the traffic and the congestion dies.

      It's a rather simplistic model compared to internet switches, but it sort of works. If you don't overload the switches, you'll have less network congestion. Less Network Congestion=Faster Communication

      • Re:Hmmm (Score:4, Funny)

        by Korbeau ( 913903 ) on Thursday August 14, 2008 @12:38AM (#24594827)

        I know that person that slows down to give place in heavy 3-lanes traffic at rush hour ... he's an asshole!

      • Re:Hmmm (Score:5, Informative)

        by thelamecamel ( 561865 ) on Thursday August 14, 2008 @12:40AM (#24594849)

        Sort of. At the moment, all routing is done electronically. The electronics doesn't have as much bandwidth as the fibres feeding it due to slow response times of electronics. So whenever three or more fibres join, you have an information bottleneck. It would be wonderful if this routing could be done optically, allowing much higher bandwidth routers, removing the bottleneck.

        But a router is a bit like a set of traffic lights - if two packets of information travelling to the same destination arrive the router at the same time, then one of them needs to be delayed while the other one is sent through. This requires some way of slowing pulses of light.

        Today, these people are claiming that metamaterials will be useful for slowing light, and would thus be useful in such an optical router. I'm a tad skeptical about this at the moment (not sure what the losses would be), and there are several other challenges that need to be met in order to create an optical router.

        • The nature of the evolution of the technology makes funny workaround. I believe the case held true for the current situation (at least in state... maybe not in my country where cabled LAN still dominate) The best model would be electronic - fibre - electronic Or use fibre all together... which is not feasible for now.
        • A prof of mine does work in metamaterials, he says he's made materials with resistivities less than 1e-9 which is an order of magnitude better than copper. Which using physics, is the same amount of decrease in loss. The important thing is dielectric constant for slowing down the speed of light, or realitive permeability

      • Re:Hmmm (Score:4, Interesting)

        by tolomea ( 1026104 ) on Thursday August 14, 2008 @01:49AM (#24595261)
        This isn't a congestion issue, it's a buffering issue.

        When a packet gets to a network device the body is stored in attached ram and the header is pushed into the routing engine which determines the egress port and queues the packet for TX. When the packets turn for TX comes up the body is retrieved from the ram and pushed down the line.

        That memory interface is one of the biggest pain in the rear parts of building a high capacity router.

        Now if instead of storing the body in ram you could spin it out around a fiber loopback that'd be mighty handy. You'd save yourself the time and effort of converting, storing, retrieving and reconverting 90% of the data.

        Unfortunately life is not that simple, at 10gigabit you get 33bits per meter. That means that a 1500byte frame occupies about 360m, even if you could knock the speed down 90% you would still need 36m of whatever. And that's just so that you can get it all out before it starts coming back in again.

        • Re:Hmmm (Score:5, Informative)

          by cnettel ( 836611 ) on Thursday August 14, 2008 @03:28AM (#24595735)

          Unfortunately life is not that simple, at 10gigabit you get 33bits per meter. That means that a 1500byte frame occupies about 360m, even if you could knock the speed down 90% you would still need 36m of whatever. And that's just so that you can get it all out before it starts coming back in again.

          Your math is off. If we move a wave from one medium to another, the frequency will be preserved, not the wavelength. The "width" of a singal in a slow medium will be far lower as well.

          • Re: (Score:3, Informative)

            by tolomea ( 1026104 )

            Good point, so since speed = wavelength x frequency, my example of a 90% speed drop will also produce a 90% drop in wavelength so the 360m packet will now occupy 3.6m.

            However my implied point that you are going to need a lot of this stuff in your router still holds.

          • Nope, I was right to start with, the speed change is a result of the wavelength change. And of course the total length changes with the wave length

      • This is not about traffic congestion but about eliminating electronics as much as possible from the network. An all-optical network is faster and less complicated. Going optical to electrical and back to optical again adds latency, and it is difficult to get electronics to operate as fast as you can push the optical signal.

    • Re: (Score:3, Insightful)

      by DirtySouthAfrican ( 984664 )
      I think the point is that the light pulses are slowed down enough that they can be manipulated by optical switches. By eliminating two conversion processes, the time between when the pulse arrives at the switch/router/booster and when it leaves is still shorter than with the electronic system. As far as I understand, it isn't related to reducing congestion by "slowing down" packets.

      • Re: (Score:3, Informative)

        by thelamecamel ( 561865 )

        Latency vs. bandwidth: ping times vs. download speeds.

        The big advantage of an optical switch would not be a decrease in ping times, the advantage is that the switch has far higher bandwidth. Optical components have much faster response times than electronics, so in theory can support many more bits/sec.

        • I'm not an expert, so maybe I'm missing something obvious, but if all the switches slow down light, won't it be traveling at different speeds based on the number of hops?

          If I understand correctly it is not rebroadcasting the light, its routing it? If this is just to split and route the spectrum to different wavelength repeaters, then I would guess this isn't an issue. Maybe its being slowed so slightly it won't cause an issue either. The article was not very detailed about the process.
          • It should only be slowing down in the switches, while passing through the metamaterial. After the light exits the metamaterial it'll speed back up.

      • Re:Hmmm (Score:4, Insightful)

        by thelamecamel ( 561865 ) on Thursday August 14, 2008 @01:07AM (#24595019)

        And I should point out that the pulses need to be delayed/buffered as part of the switching process (to avoid packet collisions) - an optical buffer using slow light will be one component in an optical switch.

    • Am I the only one who thinks that sounds a bit paradoxical?

      Nah, at nearly the speed of light "slower" and "faster" are relative.

      • Actually several years ago a group slowed light down to 17m/s, slower than a bicycle. But that was a very different technology to metamaterials.

        • Re: (Score:1)

          by kd5zex ( 1030436 )
          I would say 17 meters per second is faster than a bicycle operated by a average cyclist unless it is going downhill.

  • Riiiight... (Score:1, Funny)

    by Anonymous Coward

    'The ability to slow the light could be a tremendous force for telecoms that is sure to enhance speed and efficiency'...
    Yeah, there's a real big chance that (at least US) telecoms are going to bother for a looong time.

    • On the brighter side, we now have a better idea of what exciting new technologies to expect in 2109 [slashdot.org] (benevolent robot overlords permitting, of course)...

    • Re: (Score:1, Funny)

      by Anonymous Coward

      Is this like Little Bobby Tables?

  • More info (Score:5, Informative)

    by ipX ( 197591 ) on Thursday August 14, 2008 @12:23AM (#24594713)

    "The metamaterials work of Professor Xiang Zhang and his team at the University of California at Berkeley is being highlighted in a paper Wednesday in the online version of the journal Nature and in another appearing Friday in the journal Science."

    http://www.newsfactor.com/story.xhtml?story_id=61321 [newsfactor.com]

  • Repeaters (Score:5, Interesting)

    by internic ( 453511 ) on Thursday August 14, 2008 @12:28AM (#24594747)
    I thought one had to use repeaters every once and a while (every few km?) anyway in fiber optics, which AFIAK work by doing just what this is talking about avoiding, translate light into electrical signals back into light. Why is it so bad to have this conversion happen at the switch if it's already having to happen periodically anyway, and won't using this technique probably just result in more repeaters in the network? Or is it just that the process of multiplexing and de-multiplexing (if I have the term correct) is particularly slow? Can anyone with more detailed knowledge of these systems comment?

    • Re:Repeaters (Score:5, Informative)

      by thelamecamel ( 561865 ) on Thursday August 14, 2008 @12:53AM (#24594933)

      All-optical regenerators (i.e. repeaters) have been developed - I'm not sure whether they've been implemented yet or whether there's a bit more work to be done (I'm not sure whether they support multiple channels yet), but it's certainly a much simpler problem that's much closer to being solved than optical switching.

      Fibres can handle much more data than the electronics, so we multiplex the output of 64 electronic systems, send all that down a single fibre, demultiplex it (i.e. split it back into 64 separate fibres) and feed these signals to 64 sets of electronics. I'm pretty sure the multiplexing/demultiplexing is fast, but the problem is that you need 64 electronic routers.

      Optical switching would allow much higher bandwidth per channel, meaning you can replace the 64 channels by one, and you'd only need one optical switch rather than 64 electronic ones.

      • Re:Repeaters (Score:5, Informative)

        by Animats ( 122034 ) on Thursday August 14, 2008 @01:11AM (#24595045) Homepage

        Fibre optic amplifiers [wikipedia.org] have been all-optical for about ten years now. It's a neat technology; there's a section of erbium-doped fibre that's made to almost, but not quite, lase, by pumping the atoms up with an external laser light source that's at a lower frequency than the signal. The signal then pushes the fibre over the threshold where there's laser-type activity, and more photons come out than went in.

        • Re:Repeaters (Score:5, Informative)

          by thelamecamel ( 561865 ) on Thursday August 14, 2008 @01:21AM (#24595097)

          Yep, but if these are just amplifiers then they amplify the noise too, so every now and then you've got to tidy up the signals and remove the noise, "regenerating" the signal. This is currently done electronically and is another bottleneck. I've just asked a colleague and all-optical regenerators are still being developed.

    • Re: (Score:3, Informative)

      by Matt_R ( 23461 )

      I thought one had to use repeaters every once and a while (every few km?) anyway in fiber optics, which AFIAK work by doing just what this is talking about avoiding, translate light into electrical signals back into light.

      They have optical amplifiers these days. http://www.pipeinternational.com/index.php?limitstart=70 [pipeinternational.com]

    • Re: (Score:2)

      by Renraku ( 518261 )

      Depends on the type of repeater. If its a dumb repeater (invisible to the software layer) it can be made to repeat much faster than something like a router, that must interpret the data, process it, pack it, and ship it back out.

      The traffic analogy exists. If there are no cars in front of you, you can go as fast as your car and the law will allow. IF there's a car in front of you, a single car, your speed can only be lower than that. With each car ahead of you, it increases the chance that you'll be beh

    • I thought one had to use repeaters every once and a while (every few km?) anyway in fiber optics, which AFIAK work by doing just what this is talking about avoiding, translate light into electrical signals back into light.

      It is up to 3000m (3KM) per repeater - with a maximum of two repeaters.

      An alternative approach is to use an optical amplifier. These amplifiers directly amplify the optical signal without the need to convert the signal back into an electrical format. The amplifiers consist of a length of fibre optic cable that is doped with a rare earth mineral named Erbium. The treated fibre cable is then illuminated or pumped with light of a shorter wavelength from another laser and this serves to amplify the signal that

  • Bah! (Score:4, Funny)

    by FilterMapReduce ( 1296509 ) on Thursday August 14, 2008 @12:29AM (#24594755)

    C'mon, if we ever want to overcome the limits of general relativity and make interstellar travel commonplace, we should be trying to invent ways to make light go faster, not slower!

    You know, like on Futurama... right?

    • Re: (Score:2, Interesting)

      by Tubal-Cain ( 1289912 )

      I think I read somewhere (/.?) that one physicist tried beaming a light through a metal block (I think it was copper) to test how much got through, and found that what little made it through the metal block arrived at the sensor faster than the control test (about 5x c?).

      • I believe that experiment was related to Quantum tunneling [wikipedia.org]. Essentially the photons that made it to the sensor couldn't have gone through the block without being absorbed, but instead tunneled past it. They still traveled at the speed of light, but the distance they had to travel was decreased by the thickness of the block, resulting in a higher apparent speed.

    • Re: (Score:1)

      by taff^2 ( 188189 )

      actually no! By making light travel slower, it should be easier to travel faster than it.

  • It's not slow light... (Score:4, Funny)

    by LynnwoodRooster ( 966895 ) on Thursday August 14, 2008 @12:49AM (#24594905) Journal
    It should be referred to as velocity challenged.
  • was the picture caption:

    "Metamaterials might mean the end of all these wires"

    I initially thought the subject was over the journalist's head.

  • Another idea (Score:5, Funny)

    by narcberry ( 1328009 ) on Thursday August 14, 2008 @12:59AM (#24594979) Journal

    Or we could remove the unconstitutional packet sniffing equipment on the backbone.

  • So how does the "meta material" know where to route the traffic ? Surely the information is in the stream and to read it you have to convert it first. It's not the speed that's the problem, it's getting the routing information from the stream. If you can read the data directly from the stream, why slow it down at all ?

    • Re: (Score:3, Informative)

      by thelamecamel ( 561865 )

      This article is claiming that metamaterials can give slow light. An optical switch needs a slow light component - where electronic switches can delay packets by temporarily storing them in memory, in an optical switch it would be easier to delay packets by slowing them down rather than stopping them outright. You'd want to delay a packet if it was about to collide with another packet. The actual routing would be done by optical logic, which is very hard and not being claimed by this research group.

      Slow l

    • Re: (Score:1)

      by Melkman ( 82959 )
      Indeed, they can claim the eminent death of slow electronics all they want. But the hard part these electronics do simply isn't possible with optics and probably won't be for a very long time. That hard part is as you say getting to the routing information and change the flow of light depending on what you find.

      Basically with this light slowing material they made an optic version of a microstrip. Now if only the could make a small optic transistor.

      The nice property of photons is they don't really interact

    • Yes but if you think of it like a relational database you can trick it into doing both at the same time.

      The idea is you only convert the relevant frame (the routing information) into electrons. Process it. Then pass along the bulk of the data optically.

      So the Relational Database example would be to only query the PK and an FK column. The bandwidth then is minimal for the query results. The application processes then finds the row it wants and requests the entire row's contents. In this case you've sav

      • That's a good idea, however you'll still need to buffer (slow) that bulk of unconverted light while you convert the routing frame... and indeed, how do you know which is the routing frame without converting and reading it? Possibly a standard could specify that every Nth frame is a routing frame, but slowing the following light while that first frame is converted is still necessary.

        • Well I don't know much about large datacenter switches but I would imagine you have a lot more flexibility in how the data is segmented when it's traveling across your pipes.

          If we're just talking about the big fat pipes and this technology could justify it you could normalize the packet sizes at the fringes and pass it into the backbones as a normalized optical packet. Then you would know exactly where the routing information was located.

          A little bit of bloat in exchange for significant increases in speed

    • Re:question (Score:4, Funny)

      by Icarium ( 1109647 ) on Thursday August 14, 2008 @04:23AM (#24596029)

      I had a vision of a Japanese commuter waiting for a Bullet train, but the train destination was written on the front of the train and the train didn't stop. Not much of an analogy, but a funny image nevertheless.

  • Demux != routing (Score:4, Informative)

    by Timbotronic ( 717458 ) on Thursday August 14, 2008 @01:30AM (#24595157)
    Demultiplexing multiple channels from an optical fibre isn't routing. This technology could speed the mux/demux stuff up tremendously (saving a lot of cable) but you'll still have a bottleneck at the actual routers that need to read and direct individual packets.

    • Optical networks nowadays are not simple point-to-point fiber links. What researchers are forever working on, are ways to move more and more of the network (including switching and routing like functionality) into the optical domain. We are not talking about simply mux/demux of multiple wavelengths on a single link. We are talking about optical routers and switches.

      See this tutorial on all-optical networks [wustl.edu].

  • Correct me if I'm wrong (knowing /. that will happen in about 8 seconds) but if you slow down light enough wont that turn light into an electron? Wont that completely defeat the purpose?

    • Re: (Score:1)

      by srjh ( 1316705 )

      No, slowing down light does not turn it into an electron.

      [resists the temptation to use a car analogy]

    • Read about bose-einstein condensates and how they can hold light wave forms for long periods.

      This site [nist.gov] may be of some help.

  • It's a way to do optical buffering in routers (Score:5, Informative)

    by Animats ( 122034 ) on Thursday August 14, 2008 @01:41AM (#24595231) Homepage

    What this is all about is finding some way to do short-term optical packet storage in switches. As yet, there's no optical equivalent of RAM. All-optical gates can be built, and simple logic is possible, but there are no good storage elements. So at present there are optical switches (no queueing), but not optical routers. In order to combine packets from multiple input paths to a single output path, some of the packets need to be delayed until there's free time on the output path. Routers have output queues in RAM to do this. The idea here is to find some way to do this without RAM.

    Optical delay lines are simple enough; they're just sections of fibre optic. There are designs for pure optical routers which have little delay loops to which packets can be diverted while waiting for free time on an outgoing line. The delay is fixed, so this sort of thing tends to work better if all the packets are the same size, as in ATM. This new material, where propagation speed varies with light frequency, might be useful as a variable-delay storage medium. Maybe.

    This is an area of much active work. Several clever ways have been developed to work around the no-RAM problem. Sort of. None of them are really satisfactory, in the sense of being able to build an optical router that does what an electronic router does now. The network backbone has to be designed around the limitations of the optical technology.

    (Note that some optical switches are referred to by their vendors as "routers". They're not. Some of them, the ones with MEMS mirrors, for example, are circuit switches, like a classical phone switch.)

    • One major area of research that deals with this issue is Optical Burst-Switching (OBS). Packets are assembled at an ingress edge-node into bursts. A burst header pack (BHP) is sent before the burst to reserve resources at the optical switches along the path the burst will travel. The BHP must be converted to electronics along the path, but the data burst travels through the network optically, and only converted back to electronics at the egress edge-node. There are a lot of issues plaguing OBS - primari

      • Re: (Score:2)

        by Animats ( 122034 )

        One major area of research that deals with this issue is Optical Burst-Switching (OBS)

        The basic problem is that optical circuit switching components are available, but trying to build packet switches out of them is painful. "Burst switching" is such an attempt. Matisse Networks sells something called EtherBurst, but it's not clear that anyone ever deployed it. This is clearly an interim technology, and few network operators want to commit to it.

  • one teensy step for the tubes (Score:3, Informative)

    by Ancient_Hacker ( 751168 ) on Thursday August 14, 2008 @06:44AM (#24596795)

    Delaying or buffering the analog light signal is just a teensy part of the process. A typical packet needs to be detected, isolated, have its CRC checked, be inspected, have its addresses twiddled, have the CRC recalculated, and then queued for forwarding. It's gonna be really hard to do these things optically.

    In addition most optical delay devices are going to have a strong phase shift over frequency characteristic, a very bad thing.

    Methinks the materials folks should stick with what they know and not speculate on the uses.

     

  • ...what these guys [wikipedia.org] had to go through.

  • Great! (Score:2, Funny)

    by bothwell ( 1272132 )
    Now the telco companies will have another way to missell their "faster-than-the-speed-of-light" broadband!
  • Just install a powerful magical force field... That'l slow light down easily.

  • "However, if the light signals could be slowed during the switching process, they would not need to be converted into an electrical signal."
    It's seems, like they want remove "conversion into an electrical signal" (slow part).
    P.S.
    I thought, speed of light is constant :)

    • P.S.
      I thought, speed of light is constant :)

      /quote

      For a given set of conditions(in a vacuum, e.g.) They want to change said conditions at the "choke points" from what I can tell.

  • Here's an idea, what if you used one of these ideas at a fiber termination point? You "read" the signals header using part of the light ray, and divert the rest of it to the "slow buffer". After a few microseconds, the path is chosen, and the light ray is reflected back into the system, outputing to another fibre... Or is that just silly? Sounds like optical switching to me, although it does lead to degradation of the signal, presumably a repeater could be integrated into the system?

    • Re: (Score:3, Informative)

      by dotwaffle ( 610149 )

      This is using cut-through, not checking the CRC etc. It's just using a vessel with a known return time to "store" the packet while the route is chosen.

      I guess technically it's a hybrid of S&F and C-T.

  • slow down the net with software, not hardware (Score:2, Funny)

    by Anonymous Coward

    I recommend Microsoft products.

  • Comcast... (Score:3, Funny)

    by Darkness404 ( 1287218 ) on Thursday August 14, 2008 @03:18PM (#24603879)

    Researchers believe that it may be possible to increase the speed of the Internet by slowing down certain parts of it

    Didn't Comcast already try that?

  • A few years back a Boulder, CO based company by the name of Network Photonics had successfully created an OOO switch however the telco situation at the time forced them to shut their doors. However it was very nice piece of tech that implements on method of not having to do an electric step in switching (not quite the same method as described in the article).

Slashdot Top Deals

"Here's something to think about: How come you never see a headline like `Psychic Wins Lottery.'" -- Comedian Jay Leno

Close