Each year, PhD students from around the world apply for the Facebook Fellowship, a program designed to encourage and support promising doctoral students who are engaged in innovative and relevant research in areas related to computer science and engineering at an accredited university. As a continuation of our Fellowship spotlight series, we’re highlighting 2020 Facebook […]
Each year, PhD students from around the world apply for the Facebook Fellowship, a program designed to encourage and support promising doctoral students who are engaged in innovative and relevant research in areas related to computer science and engineering at an accredited university.
Nofel is a fourth-year PhD student at the University of Pennsylvania, advised by Vincent Liu. Nofel’s research interests lie in the broad areas of distributed systems and networking, in addition to a number of related topics. His recent work aims to design a fine-grained network measurement tool and to see how we can use those measurements to understand network traffic patterns.
Nofel is fascinated by the internet and how it allows us to communicate worldwide, from anywhere, at any time. “The sheer complexity of the network system deployed to keep the world online intrigues me to understand it more,” he says.
This led Nofel to pursue a PhD in network systems, where he could explore the many types of devices deployed to various systems — servers, switches, and network functions. Through his research, a question emerged: How do we currently monitor networks, and is there a way to monitor them more effectively?
“Networks keep getting larger and larger, and as they expand, we need more innovation to handle the scale and growth of the network,” Nofel explains. As networks grow, the question of how to monitor network status and performance becomes more complex. Humans can only monitor so much, and the reality of expanding networks necessitates a tool that can automate network monitoring. These questions led him and his collaborators to the creation of a tool called Speedlight, a fine-grained network measurement tool that can help us better understand network traffic patterns.
Speedlight has been deployed and tested in small topology, but Nofel hopes to scale his work on Speedlight to address the needs of larger networks. “Networks are constantly evolving, and will require more research and innovation to bring new solutions that can handle huge networks,” he says, and scaling network monitoring tools will need to address challenges in deployment and traffic. Through the Facebook Research Fellowship, Nofel has connected with Facebook engineers in an effort to understand the industry problems that larger data centers face in terms of monitoring so he can focus his work more intensely.
“I asked myself, ‘How can networks be self-driving?’” he says. “How can they monitor and debug by themselves? How do operators select what to deploy in their own data centers? How do they choose what to run and what not to run?” Nofel is excited to pursue additional research and investigate how networks can integrate machine learning and deep learning into further evolutions of monitoring, as they are a natural extension to develop self-monitoring networks.
To learn more about Nofel Yaseen and his research, visit his website.
The post Facebook Fellow Spotlight: Pioneering self-monitoring networks at scale appeared first on Facebook Research.
Source: Facebook AI Research