Is the Internet about to collapse from a flood of traffic? Or is it suffering from too little traffic? The growing media hype, with its frequent references to exafloods of video choking the Internet, uniformly points to the former. But Internet traffic growth, while still vigorous, has been slowing down, and the latter may be the more serious threat.
The rate of growth on the Internet is critical for the future of the core network, for the backbone providers, and for their suppliers of fiber, optoelectronic systems, routers, etc. (It is not as critical for other segments, since some of the most profitable services, such as SMS, and wireless in general, generate very little traffic.) Which technologies will be needed depends critically on this growth rate.
As just one example, Larry Roberts, one of the "Fathers of the Internet," continues his long, and so far futile, campaign to prove that his creation was a mistake, and that we should move back towards circuit-switching approaches. There are arguments that his solution may not be the right one. But even aside from that, it is questionable whether the problem that Roberts identified exists. His claim is that Internet traffic is growing at about 100 percent per year, and that router technology cannot keep up. But the evidence we have from our Minnesota Internet Traffic Studies (MINTS), although not definitive, strongly suggests that traffic is growing at only 50 to 60 percent per year both in the U.S. and worldwide. If those rates continue, the problem that Larry Roberts poses may not materialize.
The danger in settling for low growth rate projections is that we may not have enough transmission capacity to handle new demands. And, as outlined at MINTS, there are huge potential sources of additional Internet traffic. As just one example, there is already far more stored data as well as broadcast video than is seen on the Internet. And the past should have taught us to anticipate the unexpected, such as the browser, P2P, YouTube Inc. Thus there is certainly an argument for having ambitious plans. Even today, without any new technologies or services, we find traffic levels in places like Hong Kong and South Korea that are about six times those of the U.S. on a per-capita basis.
The danger in accepting exaggerated growth projections is that we may end up with another painful glut. However, the glut is not likely to be as severe as the one that led to the telecom "nuclear winter" earlier in this decade. There is no sign any more of those preposterous "Internet doubling every 100 days" stories that John Sidgmore and Mike O'Dell used to delude the industry with. The highest rates one ever hears projected are occasional mentions by John Chambers of Cisco Systems Inc. (Nasdaq: CSCO) of five- to six-times annual growth rates in the future, and that seems to represent just wishful thinking. The 4x growth cited in a recent report is not credible, since it relies on a projection made by Larry Roberts in 1999, and results in current traffic levels in the U.S. of several tens of megabits per user, clearly nonsense.
Most reports project far more modest growth rates. Larry Roberts is now only suggesting 100 percent annual growth, and that is also the rate underlying the recent Nemertes Research study. Others, such as the Cisco white paper, project growth rates to continue at around 50 percent per year. Even the recent Gilder-Swanson study warning of the dangers of the exaflood, is actually assuming just a 54 percent annual growth rate.
Now, annual traffic growth rates of 50 percent, when combined with cost declines on the order of 33 percent, result in no net increase in costs to provide the increased transmission capacity. In a competitive environment, that means no increase in revenues, which is hardly a cheering prospect for the industry.
If traffic growth could be pushed back towards 100 percent, where it used to be for many years, we would have pressure for increased revenues, and also for new technologies (whether Larry Roberts's flow-aware routing, or others). And that would be a much nicer environment for the industry and for the economy as a whole, with greater opportunities and needs for innovation.
So a tentative conclusion is that the industry should worry more about inducing higher growth rates of Internet traffic, and less about imposing limits. That there are grounds for concern is shown by the example of Hong Kong (see MINTS for links to detailed government-collected statistics). Traffic levels there are about six times those of the U.S., and the speeds of residential connections make those in the U.S. seem laughable. Yet traffic growth in Hong Kong has decelerated, and at the end of 2007 was down to almost 20 percent per year. Such rates, far below rates of progress in transmission technology, should strike fear in the hearts and minds of telecom professionals.
We need more solid data on Internet traffic. The secrecy that led to the perpetuation of the "Internet doubling every 100 days" myth and the resulting collapse is still a threat, even if a less severe one. There are already a few government and cooperative industry data collection efforts, with pointers at MINTS, which have not resulted in any visible harm to any participants. Better information sharing about what the real traffic levels are would be healthy for service providers and their vendors, and would let us decide for certain whether we are being menaced by too much Internet traffic or too little.
— Andrew Odlyzko, Director, Interdisciplinary Digital Technology Center, University of Minnesota.
. With the popularity of the internet and the explosion of user generated contents, it would be very difficult to convince folks that internet growth will slow down in the near future. It seems opinions are divided on this issue which probably may stem from the variables use in computing internet traffic growth:
People on the opposing side of your take on this issue would that we can never have too much bandwidth and that as we expand bandwidth infrastructure, people will inevitably come to use it. But how quickly will they come? I think gauging from the manner in which society is embracing everything that is web base, i don't see any danger in preparing for the worst case scenario.
Who would had thought we would be talking about exhausting the internet
capabilities. Throughout the years we have always seen how the internet is
thought of as the Universe. Something that exists, it's incredibly large and
probably immeasurable.
As human needs and imagination has been let free, we can truly assess that
there is nothing larger than the human imagination.
As more and more countries close their digital gap, the internet will
continue to "choke". But that will also come with more resources for
R&D. This, as you very well mention, could not be enough and eventually it
does get saturated - who knows?
The sooner we start thinking of the "internet" as a scarce
resource, we can understand the eventual problem. And it probably wont be the most
important or close - for now - but definitely something to think about.
I'm encouraging citizens to look to build their own community fiber networks (see http://communityfiber.org.) The model is to deliver to any end-user at a speed of 1gbps (to begin with; unless 10gbps devices are commodified by the time of deployment, in which case we'll hand people 10gbps!) The model also says the users will pay "utility rates" for the service, since the service will be operated as a public utility. So, 1gbps for perhaps $25/month.
The point here is that when a community (municipality) builds its own network, it does so with sufficient headroom to insure adequate flows even with the majority of users using whatever committed bit-rate they're allocated, which should be enough for a TV stream or two and a few other activities (like VoIP.) Traffic within the municipal fiber zone should never be an issue.
As municipalities are wired, they will interconnect - certainly, in a place like the SF Bay Area, most towns are adjacent to other towns. The interconnection would be fiber as well. These being new networks, we're building capacity as we go. We'll be building, essentially, a "new" internet - this time, one the citizens control, without reference to "Telephone Companies" and without risks to Net Neutrality or Corporate Spying and Filtering, and with a level playing field.
I don't see "routing" being that much an issue in this case, should it emerge - when, for example, Berkeley runs its own fiber network, residents of Berkeley will get to "the internet" via Berkeley's connection(s) to it - and data will be sent to the head-end of the Berkeley network to get to Berkeley residents. Routing tables will not explode.
I agree that intuitively it seems that there may be a 'natural' limit to how much bandwidth a person can consume, so there also should be a limit to how much total Internet traffic there will be eventually: just multiply the per capita volume by the population of the developed world and you have your target (some people mention machine-to-machine communication as a next wave of traffic growth, but I can't imagine that to be much more than telemetric data).
Everything else aside, that still is a 7x growth from where we are today. Add in nations like China and India developing for another factor 2 to 3, and I think people like Larry Roberts raise a valid point by questioning whether current routing technology and paradigms are fit for that job.
Even if routers can be scaled to handle 10 to 20 times of today's traffic volumes, I'd say that it is likely that there will be innovations in equipment that allow carriers to handle that traffic at a lower cost, for instance optical switching, as I pointed out in my reply to Larry's article, and another recent article on this site. Ultimately, even at low levels of traffic growth, I can imagine a sustained market for equipment replacement, provided that innovation finds ways to reduce carriers' OpEx: less floor space, lower power consmption, fewer craft interventions, etc.
But are traffic levels in Hong Kong and South Korea a good indication of what the human limit is? Or has it just stalled because the next bandwidth-hogging technology - say telepresence, just to give an example - isn't priced at mass-market levels yet?
I agree that we need more solid data on Internet traffic. Although I don't believe any credible source would suggest a doubling of Internet traffic every 100 days, even an annual growth rate of 50 percent is huge. The Cisco white paper you referenced predicts a growth rate of about 600 percent from 2005 to 2011. For those of us that like big numbers, the backbone Internet traffic in 2005 was estimated to be 1.8 TB/month and predicted to increase to 10.8 TB/month by 2011.
Whether these numbers are accurate isn't important. The exponential growth that everyone predicts will eventaully saturate the backbone networks unless better core technologies are deployed. Instead of eliminating routers, I believe the solution is to replace the SONET transport networks that still make up the Internet core, and move all routing and switching out of the core to the edge networks. An optical core with IP routing performed in the edge networks (IP over DWDM) could be such a solution.
I agree with Leo that there is an obvious ceiling on use and that we
can calculate how much bandwidth we'll need by merely multiplying the
"floor" (e.g. 10 dedicated mbps per consumer) by the population. To
hear some people predict doom, we seem to be being asked to imagine
that each and every user will be trying to send each other the Library
of Congress hour upon hour. We know that most consumption is casual,
and we know to run caching servers at all borders to reduce
retransmission from the source. The hard problems will be real-time
data, but using a community-based model, one enters a municipal zone
with one feed and it becomes the job of the municipality's routers to
do the distribution work. The only cause for congestion versus the
predictions would be the failure to build local networks for efficient
distribution (in other words, leaving the state of affairs to the
incumbents.)
I have to say that I am suprised that in our age where research is so far advanced it is amazing that we do not have difinitive information to decide where the balance lies.
Either way unless we can get information that helps us to find to which "thinking" reality points, we will have to wait it out and see. Not a good feeling. I hope that we can quickly find out what the real status of Internet traffic is so that necessary action can be taken to keep this useful tool meaningful to our lives.
I didn't say the FCC was going to interfere - I was referring to the
likes of AT&T and Comcast. The article you cite refers primarily to
Comcast.
I don't know how BitTorrent "games" TCP to get a
'competitive advantage' in seeking bandwidth, and it doesn't bother me
to slow down BitTorrent users if the BitTorrent application is such a
bandwidth hog. The article shows up the problem: Comcast doesn't have
enough capacity to sustain their advertised rates to their users. If I
have a 16mbps circuit, I should be able to download things at 16mbps
(all else being equal and ignoring whether "the internet" can deliver
at that rate.) WHAT the traffic is, shouldn't matter then, be it
BitTorrent or IPTV or VoIP or just FTP. Comcast wants to sell something
they can't really support, and as usual for corporations, they rely on
their TV ads to convince people they're getting a great service - and
they hope their users are lamers who don't actually use the service
that much. And those will be the happy campers they interview for
testimonials. ISPs are familiar with 'oversubscription' - you know that
your 20 clients won't be going after your service X all at the same
time, so you don't have to provide 20 units for 20 users - perhaps only
10 to serve 20, or whatever observation and statistics shows you.
Comcast is complaining that the BitTorrent users are eating up all the
slack, in essence, and it means Comcast doesn't provide enough slack
(capacity.) I tend to look askance at BitTorrent as I've only seen it
used to download stuff that I consider "fluffy" - ripped-off audio and
video material. And while I don't side with the content producers who
insist that every copy of X must be legal and sold for full price, I
don't sympathize with the expectation that the stuff teenagers
compulsively download hour upon hour warrants building new
infrastructure to support the illegal download habit. That is,
BitTorrent use would fall off by 90% if it weren't being used to grab
stolen data, and as an ISP I'm not going to bust my hump to see that
17-year old Joe can rip off all 250 songs he wanted to steal today - he
can wait behind people who pay real money to do real and useful work,
yes, and screw Joe: get a job, dude. Bandwidth costs money.
When
we, the people of ___________ (name of your town) wire ourselves up
with Fiber, we'll do it with an eye to leaving a good chunk of headroom
so that surges in usage will not clobber active streams or impair
traffic. On the other hand, if "Joe 17" tries to transfer terabytes of
gratuitous downloads, I would call him on the phone and tell him: quit
downloading content unless you ACTUALLY CONSUME IT. Once Joe has
downloaded 100 hours' continuous MP3 listening, I would tell Joe: you
have 100 hours to spend offline to catch up with all that data that you just had to have, so you better use what you spent our network effort to get - pal. We don't sell water to have you dump it into the ocean, so don't waste the use of our Bandwidth, either.
Once
we have our gigabit fiber networks, people will get used to knowing
that great bodies of data are out there for the having - where they can
be LEFT until they are NEEDED. Even if you could download the entire
Library of Congress - need you? Why not just go after what you need
when you need it? It may be human nature but I'll tell you now - once
you get your gigabit line, please don't try to download truckfuls of
data to demonstrate that you can. Just do what you NORMALLY do and
marvel how fast THAT is.
The ThinkerNet does not reflect the views of TechWeb. The ThinkerNet is an informal means of communication to members and visitors of the Internet Evolution site. Individual authors are chosen by Internet Evolution to blog. Neither Internet Evolution nor TechWeb assume responsibility for comments, claims, or opinions made by authors and ThinkerNet bloggers. They are no substitute for your own research and should not be relied upon for trading or any other purpose.
The latest controversy over telecom pricing is just another episode in the never-ending tug-of-war between conflicting incentives. That the same questions arise repeatedly, going back centuries to the days when ubiquitous and affordable snail mail was a revolutionary innovation, is a source of either amusement or dismay, depending on one's point of view.
The Internet has long been touted as a major weapon in reducing road congestion, through enabling and stimulating telecommuting. More recently, it has been promoted as a means to fight global warming.But these hopes fly in the face of centuries of experience.It is likely that the Internet will play a major role in alleviating problems caused by several energy crises that we face, but this will not take place as commonly expected.
Many enterprises view high-speed broadband connections as ubiquitous. Yet in about 20 percent of the country, businesses and their employees do not have access to even DSL connections. This shortcoming diminishes enterprises' ability to support their employees.
Internet evolution has been stagnating both conceptually and in business model terms, and what is likely to bring us out of that is the concept of software-defined networking, not as it is today but in the form it will become.
The recent launch of the EchoStar XVII satellite has the potential to increase broadband satellite communications' top speed from megabits to gigabits of bandwidth. Hughes Network Systems plans to test its high-speed satellite broadband services this summer and roll them out this fall.
Over time, demand forces will change the Internet. What will this mean at the technology level? Think a combination of cloud-address technologies, like the Donabe, Melange, and Quantum activity, and the OpenFlow switching architecture.
Pew says that 53% of the US population doesn't think broadband policy is necessary. Other data shows that most consumers who don't have the Internet just don’t want it. Perhaps the Internet’s problem has more to do with content than policy. Hmmmmmm...
AT&T showed off lots of improvements to its IPTV service this week. The overall message: IP, Good! Cable, Bad! Phil predicts what it all means for the broadcast proletariat.
A Verizon/Google tablet deal not only shows that tablets are now driving the hardware/software bus, they're also capable of building new alliances between old foes.
Big-data and analytics tools enable marketers to understand customers as individuals, identifying unmet needs and addressing each customer as a "segment of one," says John Kennedy, VP corporate marketing, IBM.
New York's Metropolitan Transit Authority is conducting a pilot test of digital kiosks to guide subway users to where they want to go more efficiently and at lower cost.
The whole Amazon.reader debate is a double-stupid. It's stupid to think that there's any e-book buyer who doesn't know Amazon's URL, and it was stupider to let ICANN launch the whole free-form TLD initiative to start with.
While NFC's original goal was to enhance mobile commerce applications, it is finding its way into a number of other uses, which is creating both opportunity as well as challenges for IT departments.
Enterprises would like to move to cloud computing but are hesitant because they are concerned about providers’ ability to secure company data. Here are some tips that help to ensure that if breaches occur, the business is not left holding the bag.
Edmunds separates customers into segments based on the info it collects on its site and from partners, and uses that to push out custom content, said Brian Baron, director of business analytics for Edmunds.com, at Predictive Analytics Innovation Summit.
The IBM Smarter Commerce Global Summit in Monaco kicked into high gear today, and we've already begun to see news emerging from that lovely city-state by the sea.
Expert Integrated Systems: Changing the Experience & Economics of IT In this e-book, we take an in-depth look at these expert integrated systems -- what they are, how they work, and how they have the potential to help CIOs achieve dramatic savings while restoring IT's role as business innovator. READ THIS eBOOK
your weekly update of news, analysis, and
opinion from Internet Evolution - FREE! REGISTER HERE
Wanted! Site Moderators Internet Evolution is looking for a handful of readers to help moderate the message boards on our site – as well as engaging in high-IQ conversation with the industry mavens on our thinkerNet blogosphere. The job comes with various perks, bags of kudos, and GIANT bragging rights. Interested?
To save this item to your list of favorite Internet Evolution content so you can find it later in your Profile page, click the "Save It" button next to the item.
Email This
