In November, sixth-year PhD student Yiting Xia presented a novel approach to network design at HotNets 2016 , the 15th Association of Computing Machinery (ACM) Workshop on Hot Topics in Networks. "Hot hot hot!" was how one of the anonymous reviewers described her paper.
Xia proposed a new topology that can be easily converted in response to surges in high traffic within a data center's network. She used a familiar analogy to describe the concept. "On a Houston freeway, the traditional approach would be similar to designating certain lanes for high occupancy vehicles when commuter traffic is heaviest." In her paper, she proposed not adapting existing freeway lanes, but temporarily borrowing less utilized lanes from other parts of the grid. "By liberating very smart devices to change the cabling, we're leveraging existing infrastructure for better performance," she said.
Another HotNets reviewer described her proposal as "an interesting idea, and an impressive feat to show that it can indeed be done."
CS professor Eugene Ng said, "Yiting's convertible Flat-tree network design is simply brilliant! For years, researchers in the computer networking community have argued whether hierarchical networks or random networks are better. Flat-tree opens the eyes of the community to the possibility of having the best of both kinds of networks!"
The idea for a convertible network design first struck her in March and her research was ready to publish within six months. Although her progress may seem rapid, she attributes her success to years of focused study and research. "I don't believe in overnight success," she said. "You accumulate your knowledge and then that inspires your bright idea one day."
Photo credit: Lin Dong, Rice University Physics & Astronomy PhD student