The internet is such a slow poke.
In principle, it should operate at nearly the speed of light, which is over 670 million miles per hour. Instead, internet data goes 37 to 100 times slower than that. The technical term for this speed difference is “network latency,” the split-second delay in an Internet connection as a signal travels from a computer to a server and back again.
We can do better, says Gregory Laughlin, an astronomy professor at Yale’s Faculty of Arts and Sciences. Laughlin says we can make the internet in the United States at least 10 times faster—perhaps 100 times faster.
Laughlin and colleagues P. Brighten Godfrey of the University of Illinois at Urbana-Champaign, Bruce Maggs of Duke and Ankit Singla of ETH Zurich are co-leading a study on what is slowing down the Internet — and what can be done to make it happen. to solve it. The project, funded by the National Science Foundation, is called Internet at the speed of light†
The researchers say a number of key factors are holding the internet back. For example, the network of underground fiber optic cable routes on which the Internet depends is highly chaotic. It zigzags under highways and railroad tracks, makes detours around difficult terrain such as mountains, and typically sends a signal hundreds of miles in the wrong direction at any given time during a transmission.
Second, there is the matter of the fiber optic cable itself, which is essentially glass. Internet data is pulses of light traveling through the cable; light moves significantly slower when it travels through glass.
Laughlin and his colleagues say a network of microwave cell towers in the United States would allow Internet signals to travel in a straight line through the air and speed up the Internet.
In addition, Laughlin says, this idea has already been successfully tested on a limited scale. For example, a decade ago stock traders built a microwave network between the stock exchanges in Chicago and New Jersey to shave valuable microseconds off high-frequency trading transactions.
In their final findings, which they presented at the 19e USENIX Symposium on Network System Design and Implementation in April, Laughlin and his colleagues found that microwave networks are reliably faster than fiber networks — even in bad weather — and that the economic value of microwave networks would make them worth building.
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’ takes place in US financial markets. This required the assembly and correlation of data from various 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 motivation to reduce latency between disparate locations as much as possible, the physical telecommunications infrastructure still imposed limits that prevented signaling at speeds approaching the speed of light.
Why did this project appeal to you?
Laughlin: I like problems where physics, economics and geography intersect, and the problem of pricing is the perfect juxtaposition along those lines.
How does this approach differ from other Internet infrastructure studies?
Laughlin: A primary concern in researching the physical fabric of the Internet is often bandwidth, which is how much information a person can transmit per second on a given line. Other latency work has focused on ideas related to pre-positioning information, the idea behind content delivery networks. Our work is based on the question, “What would the solution look like if you wanted to speed up small packet traffic throughout the United States as much as possible?”
What surprised you most when you looked at what slows the internet down?
Laughlin: One thing that is very well known, but which never ceases to amaze me, is the sheer amount of information that can be transferred on optical fibres. By simultaneously transmitting light in different color bands, some highly specialized multi-core optical fibers can now carry hundreds of terabits of data per second. My formative Internet experiences took place in the late 1980s and early 1990s, so my current office Wi-Fi connection in Yale seems very fast. But it’s staggering to realize that a single fiber can now transmit data at speeds exceeding my office connection by more than a factor of a million. It was therefore surprising to realize that with the right hybrid infrastructure, the Internet can be both extremely fast and capable of carrying staggering amounts of data. But because the Internet came about organically rather than in a pre-planned, top-down fashion, it turns out that there are all these curious pockets of slow performance.
You and your colleagues have suggested that a national network of microwave cell towers would make the Internet faster. Why is this?
Laughlin: While an overlay of microwave radio towers would provide only a small, seemingly negligible increase in bandwidth for the US Internet, the overlay could handle a significant portion of the smallest, most latency-sensitive requests. This type of traffic is associated with procedures that establish a connection between two sites, involving many back-and-forth transfers, each occupying a small number of bytes. Speeding it up and taking the most physically direct routes can give you a 10-fold to -100-fold increase in traffic where it matters most. On the other hand, for applications such as video streaming, where it is possible to buffer the information, the microwave towers do not need to be used. Fiber is the right choice if you have large blocks of data that need to be transferred.
What would be required in terms of costs and commitment to create such a network?
Laughlin: In our paper, we detailed a model of a national microwave network that can transmit 100 gigabits per second between 120 US cities at speeds that are only 5% slower on average than the speed of light. [which provides the ultimate physical limit]† This network would include approximately 3,000 microwave transmission locations [that use existing towers]and we estimate it would cost several hundred million dollars to build.
Does that price tag make it worth doing?
Laughlin: We did a detailed cost analysis and it seems very clear that such a project would bring an economic benefit. The applications range from things like 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 if a site seems slow to load!
What reactions have you had to the findings of the project?
Laughlin: The team presented the findings at one of the leading networking conferences and the response has been quite positive. It is of course a big step to design a network in theory and implement it in practice. But we definitely believe it’s something that would work and be worth building.