The internet is such slow.
In principle, it should run at nearly the speed of light, which is more than 670 million miles per hour. Instead, internet data moves 37 to 100 times slower. The technical term for this speed gap is “network latency,” which is the millisecond delay in an Internet connection as the signal travels from the computer to the server and back again.
We can do better, says Gregory Laughlin, professor of astronomy in the Yale University School of Arts and Sciences. Laughlin says we can make the Internet at least 10 times faster – perhaps 100 times faster – in the United States.
Laughlin and colleagues P. Brighten Godfrey at the University of Illinois at Urbana-Champaign, Bruce Mags in Duke and Ankit Singla at ETH Zurich are co-leaders in exploring what slows the Internet down — and what can be done to fix it. The project, funded by the National Science Foundation, is called the Internet at the speed of light.
Researchers say there are two main factors holding back the Internet. For example, the network of underground fiber-optic cable paths on which the Internet depends is very chaotic. It zigzags down highways and railroads, turns around difficult terrain like mountains, and usually sends a signal hundreds of miles in the wrong direction at some point during transmission.
Secondly, there is the issue of the fiber-optic cable itself, which is essentially glass. Internet data is light pulses transmitted over the cable; Light moves significantly slower as it travels through glass.
Laughlin and his colleagues say the network of microwave radio transmission towers across the United States will allow Internet signals to travel in a straight line, through the air, speeding up the Internet.
Moreover, Laughlin says, this idea has already been successfully tested on a limited scale. For example, stock traders built a microwave network a decade ago between stock exchanges in Chicago and New Jersey in order to carve out valuable microseconds from high-frequency trading transactions.
In their final results, which they presented at 19The tenth USENIX Symposium on Networked Systems Design and Implementation In April, Laughlin and colleagues discovered that microwave networks are reliably faster than fiber networks—even in inclement weather—and that the economic value of microwave networks makes them worth the expense.
Laughlin spoke with Yale News recently about the project.
How did you become part of the internet at the speed of light?
Gregory Laughlin: I was interested in the economic problem of where “price formation” occurs in the US financial markets. This requires compiling and correlating data from different markets, for example futures markets in the Chicago metro area and stock markets in the New York metro area. When I started working on the problem [in 2008] It was clear that even when there is a strong motivation to reduce latency as much as possible between disparate sites, the physical infrastructure of communications still imposes constraints that prevent signals from being transmitted at speeds close to the speed of light.
Why does this project appeal to you?
Laughlin: I like problems where physics, economics, and geography intersect, and the problem of price formation is the perfect juxtaposition along these lines.
How does this approach differ from other checks of the Internet’s infrastructure?
Laughlin: Bandwidth is often the primary concern in studies of the physical structure of the Internet, where the concern is how much information an individual can transmit per second on a given line. Other work on latency has focused on ideas about information pre-mapping, the idea behind content delivery networks. Our work takes the perspective of asking, “What would the solution look like if you were to speed up small packet traffic as much as possible across the entire United States?”
What surprised you the most when you looked at what was slowing down the internet?
Laughlin: One thing, very well known, but it never ceases to amaze me, is the sheer amount of information that can be carried on optical fibres. By transmitting light in different color bands simultaneously, highly specialized single multi-core glass fibers are now able to carry hundreds of terabits of data per second. My formative experience online happened in the late ’80s and early ’90s, so my current wifi connection in the Yale office seems really fast. But it is astonishing to realize that a single fiber can now transmit data at a rate that exceeds a desktop connection of more than a million workers. So it was surprising to realize that with the right hybrid infrastructure, the Internet can be incredibly fast and capable of carrying huge amounts of data. However, since the Internet originated in an organic way rather than a pre-planned, top-down way, it turns out that there are all these intriguing pockets of sluggish performance.
You and your colleagues have suggested that a nationwide network of microwave radio transmission towers would make the Internet faster. why is that?
Laughlin: Although the overlay of microwave radio transmission towers would apparently provide only a tiny, seemingly small increase in US Internet bandwidth, the overlay could handle a significant portion of smaller, more latency-sensitive requests. This type of traffic is associated with actions that establish a connection between two sites, which involve lots of back and forth transmissions each with a small number of bytes in size. By speeding up these steps and actually taking the most direct route, you can get a 10 to 100 increase in traffic at the most important places. On the other hand, for applications such as video streaming, where information can be cached, microwave towers are not required. Fiber is the way to go if you have large blocks of data that need to be transferred.
What would it take to build such a network in terms of cost and commitment?
Laughlin: In our research paper, we created a detailed model of a national microwave network that can transmit 100 gigabits per second between 120 US cities at speeds that are on average 5% slower than the speed of light. [which provides the ultimate physical limit]. This network will include nearly 3,000 microwave transmission sites [that use existing towers]We estimate that its construction will cost several hundred million dollars.
Does this price make it worth it?
Laughlin: We’ve done a detailed cost analysis, and it seems very clear that a project of this nature would provide an economic benefit. Apps run the gamut from things like remote surgery to e-commerce and gaming.
How often do you think about this while downloading a document or clicking on a website?
Laughlin: Only when the site seems slow to load!
What is your reaction to the results of the project?
Laughlin: The team presented the results at one of the leading networking conferences, and the response was very positive. Of course, it is a big step from designing a network in theory and applying it in practice. But we definitely feel it is something that will work and is worth building.