The Internet is such a slowpoke.
In principle, it should operate at about the speed of light, or more than 670 million miles per hour. Instead, internet data moves 37 to 100 times slower than that. The technical term for this speed discrepancy is “network latency,” the split-second delay in an Internet connection as a signal travels from a computer to a server and back.
We can do better, says Gregory Laughlin, professor of astronomy at Yale School of Arts and Sciences. Laughlin says we can make the internet at least 10 times faster – maybe 100 times faster – in the United States.
Laughlin and his colleagues P. Brighten Godfrey of the University of Illinois at Urbana-Champaign, Bruce Maggs of Duke, and Ankit Singla of ETH Zurich are co-leads on an exploration of what’s slowing down the internet – and what that can be done to fix this. The project, funded by the National Science Foundation, is called Internet at the Speed of Light.
Researchers say a few key factors are holding the internet back. For example, the network of underground fiber optic cables on which the Internet depends is very chaotic. It zigzags under highways and train tracks, around difficult terrain such as mountains, and typically sends a signal hundreds of miles in the wrong direction at some point during a transmission.
Second, there’s the issue of the fiber optic cable itself, which is essentially glass. Internet data is pulses of light traveling through the wire; light travels much slower when passing through glass.
Laughlin and his colleagues claim that a network of microwave radio transmission towers across the United States would allow internet signals to travel in a straight line, through the air, and speed up the internet.
What’s more, says Laughlin, this idea has already been successfully tested on a limited scale. For example, stock traders built a microwave network between the Chicago and New Jersey stock exchanges a decade ago to save valuable microseconds on high-frequency trade transactions.
In their final conclusions, which they presented at the 19and At the USENIX Symposium on Designing and Implementing Networked Systems in April, Laughlin and his colleagues discovered that microwave networks are faster than fiber optic networks, even in bad weather, and that the value economics of microwave networks would justify the expense.
Laughlin recently spoke to Yale News about the project.
How did you come to be part of the internet at the speed of light?
Gregory Laughlin: I was interested in the economic problem of where “price formation” occurs in US financial markets. This required assembling and correlating data from different markets, for example the Chicago metro area futures markets and the New York metro area stock markets. When I started working on the problem [in 2008] it was clear that even when there was a strong incentive to reduce latency between disparate locations as much as possible, the physical telecommunications infrastructure still imposed limitations that prevented signaling at speeds near the speed of light.
Why did this project appeal to you?
Laughlin: I love problems where physics, economics, and geography intersect, and the problem of price formation is the perfect juxtaposition in that sense.
How is this approach different from other Internet infrastructure reviews?
Laughlin: One of the primary concerns in studies of the physical structure of the Internet is often bandwidth, where one is concerned with how much information per second one can transmit over a given line. Other latency work has focused on ideas related to information prepositioning, which is the idea behind content delivery networks. Our work starts from the following perspective: “What would the solution look like if you wanted to accelerate small packet traffic as much as possible throughout the United States?
What surprised you the most when you looked at what was slowing down the internet?
Laughlin: One thing, which is well known, but which never ceases to amaze me, is the huge amount of information that can be carried over fiber optics. By simultaneously transmitting light in different color bands, highly specialized multi-core glass fibers are now capable of carrying hundreds of terabits of data per second. My formative Internet experiences were in the late 1980s and early 1990s, and so my current Yale office WiFi seems very fast. But it’s amazing to realize that a single fiber can now transmit data at a rate that exceeds my office connection by more than a million. It was therefore surprising to realize that with the right hybrid infrastructure, the Internet could be both extremely fast and capable of transporting staggering amounts of data. Yet, as the Internet has arisen organically rather than in a top-down, pre-planned fashion, it turns out that there are all these curious pockets of slow performance.
You and your colleagues have suggested that a nationwide network of microwave radio transmission towers would make the Internet faster. Why is it?
Laughlin: Even though an overlay of microwave radio transmission towers would only provide a tiny, seemingly negligible increase in bandwidth for the American Internet, the overlay could handle a significant fraction of the smallest and most latency sensitive. This type of traffic is associated with procedures that establish a connection between two sites, and which involve many round trips of a small number of bytes each. By speeding them up and taking the most physically direct routes, you can get a 10- to -100-fold increase in traffic where it matters most. On the other hand, for applications such as video streaming, where information can be buffered, microwave towers need not be used. Fiber is the way to go if you have large chunks of data to transfer.
What would it take, in terms of cost and commitment, to create such a network?
Laughlin: In our article, we created a detailed model of a national microwave network capable of transmitting 100 gigabits per second between 120 US cities at speeds on average just 5% slower than the speed of light. [which provides the ultimate physical limit]. This network would involve around 3,000 microwave transmission sites [that use existing towers]and we estimate that it would cost several hundred million dollars to build.
Is this price worth doing?
Laughlin: We did a detailed cost analysis, and it seems very clear that a project like this would bring economic benefit. Applications run the gamut, from telesurgery to e-commerce and gaming.
How often do you think of this when you download a document or click on a website?
Laughlin: Only when a site seems slow to load!
What reactions did you have to the findings of the project?
Laughlin: The team presented the results at one of the major networking conferences, and the reaction was pretty positive. Of course, it’s a big step between designing a network in theory and implementing it in practice. But we really think it’s something that would work and be worth building.