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

 



Forgot your password?
typodupeerror
×

Bees Can Optimize Internet Bottlenecks 128

prostoalex writes "Georgia Tech and University of Oxford scientists claim bees can help up develop a better Internet traffic algorithms. By observing bees, the researchers noticed that bees pass back information on route quality. 'On a basic level, the honeybee's dilemma is a tale of two flower patches. If one patch is yielding better nectar than the other, how can the hive use its workforce most efficiently to retrieve the best supply at the moment? The solution, which earned Austrian zoologist Karl von Frisch a Nobel Prize, is a communication system called the waggle dance.' Any practical applications of that? Well, apparently ad servers, serving banners across a variety of servers, can report back on the time it took to generate the page."
This discussion has been archived. No new comments can be posted.

Bees Can Optimize Internet Bottlenecks

Comments Filter:
  • Um... (Score:5, Funny)

    by varmittang ( 849469 ) on Monday December 17, 2007 @04:35PM (#21730306)
    You know the tubes thing is a joke, right? You can't send live bees down it to figure out how to make it faster.
  • by Sciros ( 986030 ) on Monday December 17, 2007 @04:36PM (#21730320) Journal
    Man I'm not even going to read the summary or TFA no time for that time to hire a ton of bees! Forget outsourcing to China and India and Eastern Europe, teh beehive is where it's at.
    • by JPriest ( 547211 )
      It is valid though. Current routing protocols mostly calculate the best path, then send 100% of traffic over the best path even if it is congested and there is another unused path. Traffic is only shared when the paths are equal in cost, but if you have 1.3 gig or traffic destined to be sent over a 1 gig link, sending some of the traffic over a second 500 meg link, or sending it through a longer 2 hop path is better than the current practice of dumping the full 1.3 gig onto the gig link. Right now if one li
  • The bees won't have room to fly properly in the tubes. Even I know that much.
  • by toQDuj ( 806112 ) on Monday December 17, 2007 @04:36PM (#21730330) Homepage Journal
    Well, I notice that one way of optimising _my_ experience is to switch off the ads, java, javascript and plug-ins. Blazingly fast, the tubes then become.
    • by Anonymous Coward
      Why is it that the latest scientific research is always first applied to:
      1) war
      2) advertising on the net
      • Re: (Score:3, Informative)

        by gardyloo ( 512791 )
        I believe you've made a fencepost error. In this case, it will read:
              0) porn
  • by tgd ( 2822 ) on Monday December 17, 2007 @04:37PM (#21730336)
    I used to have a problem with bees around there the FIOS ONT cabling enters my house.

    Freakin' hazard going anywhere near the thing.

    And my internet is freakin' fast. They might be onto something.
    • Re: (Score:1, Funny)

      by Anonymous Coward
      Dude, fuck that! I would punch every bee in the face! Bees aren't taking me out, I'd be like, "FUCK YOU BEE!" *PUNCH* I'm not going out that way.
      • FYI: The internet does not like Dane Cook - the general consensus is that he steals his material [google.com].

        Many an internet argument have been had over this one.
        (I take neither side as I don't particularly care. Just pointing it out since you'll probably be disheartened if your post is not modded 5, Funny.)
  • by blueZ3 ( 744446 ) on Monday December 17, 2007 @04:38PM (#21730344) Homepage
    Internet researchers get hives investigating honey of an optimization tool
  • by Mike Morgan ( 9565 ) * on Monday December 17, 2007 @04:40PM (#21730374)
    From November [slashdot.org]
  • by afidel ( 530433 ) on Monday December 17, 2007 @04:42PM (#21730426)
    The problem of internet optimization stopped being a research subject years ago and is more of a business problem. Peering relationships and lowest cost routing mean that traffic will often travel a suboptimal route from a networking perspective because it is the best route from a providers financial perspective.
  • Now we'll have routers do the wiggly bee dance AND check the ping times at the same time.
    What will they think of next, EBGP? :)
    • by red_dragon ( 1761 ) on Monday December 17, 2007 @05:05PM (#21730796) Homepage

      Now we'll have routers do the wiggly bee dance

      If a big Cisco or Juniper is running WDRP (Wiggly Dance Routing Protocol), does each line card do a different dance from the other cards in the chassis? What would such a router be called then, a hoedown? If the line cards started dancing "Thriller", will the router turn white and start chatting to young boys on IM?

  • Talk about a way to get "buzz" for your Web site...
  • Web 2.0 (Score:5, Funny)

    by ruiner13 ( 527499 ) on Monday December 17, 2007 @04:46PM (#21730502) Homepage
    Bees make the best web 2.0 buzzwords. They're the buzziest! I blame the hive mentality of the marketing drones for this.
    • by jd ( 1658 )
      It is no longer called Web 2.0, that's so twentieth century. To conform to the new bee paradigm, it is now referred to as Honeycomb 1.5. Malware has also been renamed to Wasp. File transfer rates are now calculated in mead casks per unit druid. P2P systems no longer use seeds, they pollinate.
    • Somewhere someone will receive "BZ" (bravo zulu) and others will get BZZZT....

      captcha: ascends
  • Seems like it would be rather exploitable by "herding" the "bees" to another path. Would be nice to be able to be able to have an intelligent layer to networking that knew when it was having its strings pulled. All I'm saying is that it seems like any kind of error checking required for this to be stable and secure would negate any benefit from having such a dynamic network. The power of suggestion is often unnoticed, for ironic reasons.
    • by MBCook ( 132727 ) <foobarsoft@foobarsoft.com> on Monday December 17, 2007 @04:56PM (#21730682) Homepage

      What I got from reading the article was that they weren't optimizing the 'net at large but the services in one data center. By making the individual servers in the data center allocate themselves to the various hosted sites/services based on demand. Because of this, it's basically immune to external cheating, after all there is no point. If they were changing who's packets went through their network on the way to somewhere else, there would be a reason to cheat.

      The article makes perfect sense, but the domain seems a little limited to me. You have to be able to quantize things. You have to be able to shift things around (make server A be able to pick role X, Y, or Z based on which is better at the moment). In some problem sets this would be easy. For example the /. setup that was described a while back where they have a few boxes doing this, a few doing that, and they all work off the same read only NSF share. It would be easy to move the boxes that run user pages between that and static pages. It could help there.

      On the other hand, the boxes couldn't switch between being web and DB boxes very fast (you would have to load up all that data) so you couldn't let the boxes choose between those two roles (you'd lose most all your benefit from the expense of the switch).

      The choices have to be relatively homogeneous.

      • > What I got from reading the article was that they weren't optimizing the 'net at large but the services in one data center.

        In fact the internet at large can't be mapped to the behavior of bees. Bees try just to be efficient as possible, they don't need to drive traffic to a particular site.
      • Yep, and not only that but also most of the practical applications of this are already solved using load balancing devices. They can keep a pool of available servers, and allocate new connections to them either by dumb round-robin type behaviour, but also by monitoring how long each takes to respond and using that to gauge their respective load.

        There might be some classes of work where the server is actually best placed to determine its ability to perform the task, but for most things it doesn't matter if

    • by guruevi ( 827432 ) on Monday December 17, 2007 @05:03PM (#21730776)
      If you've ever "herded" bees, you would know that even if you have a full suit, they'll attack you and be successful if you agitate them. So too with us nerds, if we figure out (and it's quite easy) that you're herding us to a specific patch for ad-revenue or whatyouwant, it will sting no matter who you are and what protection measures you have.
  • by bluemonq ( 812827 ) on Monday December 17, 2007 @04:47PM (#21730516)
    Dogs [slashdot.org] with bees in their mouths and when they bark they optimize your local network and find rogue wireless access points?
  • by Overzeetop ( 214511 ) on Monday December 17, 2007 @04:49PM (#21730548) Journal
    "Beer Can Optimize Internet Bottlenecks"

    I'm not sure what the alcohol has to do with network optimization, but I'll just say right now that I'm for it.

    • Re: (Score:2, Funny)

      Beer? Alcohol? Beer isn't alcohol, it's basic nutrition!

      And, sure, beer can optimize networks. Drink enough and watch how fast everything whizzes by you!
    • by hattig ( 47930 )
      Well you'd be correct, Waggle Dance [wellsandyoungs.co.uk].

      (Hmm, since when do you have to be legally allowed to drink beer in order to VIEW DETAILS of a beer?)
      • I didn't know they were still brewing Waggle Dance - not seen it on a pump for ages.

        Nice, but definitely a summer drink.

    • Yes. And I know how it works too.
      With enough beers, you forget why you were waiting for
      a particular webpage to load, so it seems faster when
      you discover that the page is already loaded.

      Oh, wait, maybe it's pot that does that. I forget.
  • by XPisthenewNT ( 629743 ) on Monday December 17, 2007 @04:51PM (#21730570) Homepage
    The end of the article comments on how the bee algorithm also allows the data center to save power. It seems like if the data center isn't getting many requests, it can send some servers into power saving standby mode. Much like if there isn't much honey to collect, the bees stay in the hive and save energy.

    Are other web data centers able to shut down some servers at night to save power, or is it just because this data center seems configured to allow the servers to each serve any number of websites?
    • by MBCook ( 132727 )
      I would have liked to know a little more too. My guess is that instead of having 100 servers, most sitting at 2% CPU and sleeping on and off, they could consolidate to 20 servers running at 20% CPU, the rest sleeping basically all the time. Heck, using SNMP they could physically power down the boxes if they had enough free, but I doubt they would do that.
    • by afidel ( 530433 )
      Any DC running ESX 3.5 on certified hardware can shutdown and powerup host servers on demand, it's a new experimental feature. Depending on your profile you can shutdown during business hours to just essential servers and add capacity for nightly batches or have servers online during the day to handle user demand and scale back for nighttime lulls.
  • ...in the bee world. Bees don't have an economy and work for no apparent reason other than to advance the hive. If the bees worked out of self gain and received payment for every other bee that went to a particular flower; you'd see tons of waggle dancing. Eventually, the other bees would ignore them completely and all that's left is 75% of the original bee workforce attempting to get in the entrance that is constantly being blocked by dancers.
    • Re: (Score:2, Funny)

      by gudnbluts ( 1186023 )
      Which is why the research failed when conducted by analysing the waggle dances of more intelligent species - in this case strippers.
  • The concept of the individual server is dead to me. What would make sense TO ME would be a san sitting at one logical end of the datacenter, and a big cluster of apache servers sitting at the other...

    Lets say that there is a server farm hosting 1000 different websites for people to host pictures of their cats. Most of these people are not going to need a full server for their cat pictures, so lets say we have 100 web servers total. Now lets say that www.omfgmycats.com gets posted to the slashdot frontpag
    • Some hosting providers already do this. See for example, MediaTemple's Grid Servers [mediatemple.net]
    • by MBCook ( 132727 )
      That sounds like what the article was about, as I read it. It's not all that clear (because it was written for non-techies). The bee thing seemed to be about a way to get the servers to dynamically allocate themselves to various sites based on load in a way that will maximize the resources and the revenue (since they were describing a per-transaction system, doing 5 little cheap transactions may be better than 1 big expensive transaction).
    • by 0racle ( 667029 )
      I'm going to patent you idea as a 'Load Balanced Web Cluster.' I'll make millions off your original idea.

      MUHAHHAHAHAHA!
      • by blhack ( 921171 )
        A load balanced web cluster usually hosts 1 website. Almost every single major website out there runs on a cluster. What i am talking about is dynamic clustering....as in, you host 1000 websites on that cluster, and when www.foo.com is only getting a hit or two per day, it cowers back down into the corner and only uses just a little tiny bit of the resources.
    • Imagine a Beowulf cluster of those. (hint hint)
  • very cool finding ... it's inspiring to see how researchers are looking to adapt biological models to technological systems. I think that this kind of work will be[e], ultimately, very productive for helping us to see around the cognitive and material constraints that we have inherited by working from precursor technologies. I wonder if the same models could be used to improve searching.
  • If bees are the miracle that is going to make my internet faster I have a problem. I am allergic. Hopefully they will stay in the cable cause if bees start popping out of my computer I am going to have to change careers.
  • And by "bees", they clearly mean "Yellow Jackets"

    http://ramblinwreck.cstv.com/ [cstv.com]

    • by plsander ( 30907 )
      When I was at Ga Tech (83-88) they were researching beer processing too... Trying to come up with a continuous beer brewing process.

  • As long as the researchers don't converse with a bee-like Jerry Seinfield, then I wish them nothing but luck.
  • won't somebody think of the lavae!?
  • to generate advertising buzz for your website.
  • by Anonymous Coward
    I prefer pigeons [ietf.org] myself.
  • IT Support Guy 1: Well, sure is quiet in here today. IT Support Guy 2: Yes, a little too quiet, if you know what I mean. IT Support Guy 1: Hmm...I'm afraid I don't. IT Support Guy 2: You see, bees usually make a lot of noise. No noise -- suggests no bees! IT Support Guy 1: Oh, I understand now. Oh look, there goes one now. IT Support Guy 2: To the Beemobile! IT Support Guy 1: You mean your Chevy? IT Support Guy 2: Yes.
  • by foobsr ( 693224 ) on Monday December 17, 2007 @05:27PM (#21731150) Homepage Journal
    TFA: "Tovey said his collaboration with Seeley demonstrated that the communication provides a "beautiful" feedback loop to prevent one flower patch from being abandoned while another is depleted."

    Not that they seem to have ways to resolve aspects of the tragedy of the commons, no ...

    "Honey-bee mating optimization (HBMO) algorithm for optimal reservoir operation" ( link [sciencedirect.com])

    They help to improve otherways too.

    CC.
  • does the new type of network have stingers? i hate stingers.
  • now i know what will speed up the internet, everybody just switch to BeeOS...
  • blurb misleading (Score:5, Informative)

    by pavera ( 320634 ) on Monday December 17, 2007 @05:39PM (#21731358) Homepage Journal
    The blurb is very misleading, this isn't about serving ads faster, or even about banner ads reporting their load times. It isn't about routing bottlenecks either, it is about distributed loads, and dynamic resource allocation on the server side.

    The methodology used is this:
    you have a server farm, this server farm is serving up many different sites. Internal to the server farm is an "ad board" for lack of a better term. When Site A's load spikes it's dedicated server can post an ad to the "ad board" which other servers in the farm can see. Then, servers which are dedicated to other sites, but are basically sitting idle can pick up the ad, say "oh I can help out this site over here" and somehow join the load balancing cluster that is server Site A's content. If necessary, the second (and however many other servers) can also place an ad on the board, getting more and more servers included serving up Site A.

    As Site A's traffic decreases, less and less servers will be needed, so they will stop posting ads, and fewer and fewer servers will be serving Site A.

    This is about dynamically allocating resources across a large data center/cluster not serving ads on the internet or even about optimal routing of traffic on the internet, instead of having a single server dedicated to serving 1 site, you have many servers which dynamically based on load decide which sites to serve.

    • Oh, so it's sort of a server-sized, free-market based version of coral cache. Cool!
    • by DrEasy ( 559739 )
      Very good summary! Also, I don't see how observing bee behavior (beehavior?) was so instrumental in coming up with what basically is a blackboard system (you can use a tuple-space to do this) or a contract-net protocol [Smith].
  • So, maybe they aren't disappearing at all - the telco's are having them eliminated so the free-netter's can't put the bees to this nefarious use.

    http://news.nationalgeographic.com/news/2007/02/070223-bees.html [nationalgeographic.com]

    btw - has anyone made a honeypot joke yet?
    • no, but someone made a post to trick everyone into making honeypot jokes where they could easily be modded below the viewing threshold and suppressed.
  • it already exists (Score:2, Interesting)

    by Anonymous Coward
    Hey, it already exists and in widespread use... It's called the ants algorithm.
    It was developed by Marco Dorigo at the Free university of brussels http://iridia.ulb.ac.be/~mdorigo/HomePageDorigo/ [ulb.ac.be]
  • by cyngus ( 753668 ) on Monday December 17, 2007 @05:54PM (#21731604)
    Ants also do a similar thing. The difference is that they release chemicals as they travel. The more ants that travel the same path, the stronger the trail, the more likely the path will continue to be traveled. This also has some consideration for traveling velocity. All other things being equal, a faster (typically shorter) path will have a stronger chemical signature because more ants will traverse it per unit time. Further, new, potentially better, paths will be discovered on rare occasion that an ant gets lost or for some reasons falls off the established path. In artificial simulations this trailblazing can be amplified by increasing the random chance that from any given network hop, the ant/packet will choose some new direction which may be totally random or may be based on other paths that have already been traversed.
    • Now, if only scientists can add bee DNA, with ms' RNG... we could have some hella snail trails...
  • http://news.nationalgeographic.com/news/2005/10/1012_051012_hornet_video.html [nationalgeographic.com]

    The only thing this video is missing is a tiny bee Wilhelm scream
  • If I ever see my routers doing a 'waggle dance', I'm moving to another universe.
  • Welcome our new buzzing friends. However, I don't see how a bunch of bee's stuck in a tube will increase network performance....I would think it would move slower than honey on a cold day.....(wah wah wah) ;)


    there's my 2 bits of dry humor for the day...forgive me /.

  • "... a better Internet traffic algorithms."

    Huh?
  • I can't be the only one who read the title as "Beer cans optimize bottlenecks?" and wondered WTF?
  • It seems every month some new study comes out about bees or ants methods being used to improve routing algorithms - I couldn't be bothered finding the older articles (not being an ant, I failed to leave a scent trail through the internet to the articles - nor being a bee, noone's doing funny little dances to tell me where the articles are), but if there are so many 'breakthroughs'... why don't they just read each other's articles?
  • They're supposed to be the ones to optimize this stuff. Oh well, I guess they'll have to come up with some new goof-ball interview questions. "See, there's a swarm of bees passing through a cloud ..."
  • Any practical applications of that? Well, apparently ad servers, serving banners across a variety of servers, can report back on the time it took to generate the page.

    Can we please have a more productive example of a practical application?
  • imsickofshakingmybootyforthesefatjerks?
  • This is part of swarm intelligence [wikipedia.org] research, which is in fact also my own area of academic research (specifically business applications of swarm intelligence and effects on adaptability and implications for non-hierarchical self-organised companies). This journal [springerlink.com] is nice reading if you want to learn more. This conference [computelligence.org] (organised by the IEEE Computational Society where I am a member) is also of interest, but the "classic" workshop is ANTS [ulb.ac.be]. Swarm intelligence is so important that one of the first resear [wikipedia.org]

  • .. but the Internet is far from ideal. The Internet is not as resilient to attack as it was initially anticipated to be. You can have a single line go down between two sites and even though the sites both have multiple routes in and out, the traffic flow can stop completely due to dumb routing tables, commercial arrangements, and other interests. The Internet is not full of unbiased routers connected together in a mathematically ideal, impartial way. It's more like a social network.. where if two people fal
  • Sounds like a good B2B solution, but won't anyone think of the customers?
  • My sysadmin does something similar to the waggle dance everytime a user reports incessant porn pop-ups.
  • I saw my IT guy try to dance at this year's company Christmas party.
  • Here is the link to the real article at the Georgia Institute of Technology entitled Bee Strategy Helps Servers Run More Sweetly [gatech.edu].

    It's a shame that /. posted that link from a spammer instead. That spammer always copies a story 1 - 3 months after it was fresh. Probably has something to do with Google-jamming.

  • The coveredinbees tag seems to be a reference to a skit of his he did during his Glorious [imdb.com] tour:

    My father was a beekeeper before me, his father was a beekeeper before him. I want to walk in their footsteps. And their footsteps were like this... [Runs screaming] AAAAAAAH! I'm covered in beeeeees!
    Classic.

"If it ain't broke, don't fix it." - Bert Lantz

Working...