Twenty-​​five years ago, an engi­neer at CERN, the Euro­pean Orga­ni­za­tion for Nuclear Research in Geneva Switzer­land, had an idea that would change the world. Tim Berners Lee sent a memo to his col­leagues at the world’s largest par­ticle physics lab­o­ra­tory proposing a way for all of its computers—and even­tu­ally all the com­puters in the world—to talk to each other. This memo marks the birth of the World Wide Web.

Since then, the Internet has become increas­ingly essen­tial to human activity—from reading the news and buying stocks to com­mu­ni­cating and researching flu symp­toms. But it still has some problems—namely, its plumbing, according to Edmund Yeh, an asso­ciate pro­fessor of elec­trical and com­puter engi­neering at North­eastern University.

Yeh is a prin­cipal inves­ti­gator on a multi-​​university $7.9 mil­lion research project to unclog the Internet’s plumbing and fix this problem. The Internet’s basic archi­tec­ture is highly inef­fi­cient, he said, because new con­nec­tions to each piece of con­tent must be cre­ated when­ever a user wants access to the material.

If you’ve got a lot of demand for a par­tic­ular data type, it’s like water building up,” Yeh explained. That water, he said, can be man­aged in two ways—one is by get­ting it to its des­ti­na­tion drain (i.e., the data server), the other is to drill a new drain some­where along its journey (i.e., a caching point that tem­porarily stores the data).

Yeh’s research team is building what it calls the Named Data Network—one of four projects funded by the fed­eral government’s Future Internet Pro­gram. NDN main­tains a net­work of caching points, or “drains,” that are strate­gi­cally located around the core of the Internet as well as its periphery.

Edmund Yeh, associate professor of electrical and computer engineering

Edmund Yeh, asso­ciate pro­fessor of elec­trical and com­puter engineering

Con­tent dis­tri­b­u­tion net­works such as Akamai are taking a sim­ilar approach, Yeh said, but their oper­a­tions work only at the edge of the Internet and pro­vide ser­vice only to large con­tent providers such as CNN. “This,” Yeh said, “is due to the inability of the cur­rent Internet archi­tec­ture to handle caching.”

With NDN, user requests would be directed to caching points located closer to them in the Internet, regard­less of the type of con­tent they’re trying to access.

Still, a chal­lenge remains: where to place the drains and how to best direct the “water” toward them. In col­lab­o­ra­tion with researchers at the Cal­i­fornia Insti­tute of Tech­nology, Yeh’s lab at North­eastern recently released a paper on arXiv in which the team presents an algo­rithm called the VIP Algo­rithm. It simul­ta­ne­ously per­forms those two processes—both the drilling of drains and the directing of water. The processes work in a coor­di­nated manner, Yeh said, with each relying on the other and both dynam­i­cally adapting to the pre­vailing demand for content.

Inci­den­tally, the global net­work of high-​​energy physics researchers attempting to access par­ticle physics data from the Large Hadron Col­lider at CERN—where the World Wide Web was born all those years ago—also has a sim­ilar plumbing problem. But physics researchers based at the Cal­i­fornia Insti­tute of Tech­nology believe Yeh’s algo­rithms could help them unclog their net­work pipes. So the two groups have teamed up to test it out.

Indeed, Yeh’s approach is a promising can­di­date for any sci­en­tific net­work in which a global com­mu­nity of users is requesting access to a vast body of data.

We could make an impact first in these sci­en­tific big-​​data appli­ca­tions,” he said. “That’s a good testing ground for the broader Internet.”