You’re downloading a file, or calling up a Web page. Suddenly, the cyberworld goes into suspended animation.
Why can’t the Internet provide more consistent service? One reason is a lack of insight into the overall pattern of traffic on the Internet. Now, researchers at AT&T Laboratories have come up with some surprising answers to what’s going on.
If you look at a plot of traffic through a network point over a minute, the trace will fluctuate wildly from one fraction of a second to another-an expected result. Now look at a day broken up in units of 100 seconds. On a voice network, the curve flattens out; instantaneous variations cancel each other out. But on the Internet, the AT&T researchers found the pattern of traffic had the same “bursty” character over long time periods as over short ones.
Such “self-similarity”-described by a type of mathematics known as fractal geometry-occurs often in nature. A coastline, for instance, has the same jagged appearance on a large scale as on a small one. According to Robert Calderbank, vice president for information sciences at AT&T Labs, the Net’s self-similarity stems from the way people use it. Lengths of Internet sessions range over a span of 6 to 7 orders of magnitude. As a result, the flow of data on the Net resembles the mathematically complex phenomenon of turbulence.
This knowledge is allowing network engineers and service providers to rework the rules of thumb that they have used for 70 years in designing the telephone system, Calderbank says. Routers that incorporate the more sophisticated-and accurate-traffic algorithms should help data move through the Internet with fewer of those finger-drumming delays.
Geoffrey Hinton tells us why he’s now scared of the tech he helped build
“I have suddenly switched my views on whether these things are going to be more intelligent than us.”
Meet the people who use Notion to plan their whole lives
The workplace tool’s appeal extends far beyond organizing work projects. Many users find it’s just as useful for managing their free time.
Learning to code isn’t enough
Historically, learn-to-code efforts have provided opportunities for the few, but new efforts are aiming to be inclusive.
Deep learning pioneer Geoffrey Hinton has quit Google
Hinton will be speaking at EmTech Digital on Wednesday.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.