Dr. Nick Duffield, a professor in the Department of Electrical and Computer Engineering at Texas A&M University, was awarded a grant from the National Science Foundation (NSF) that will allow him to research network traffic classification.

Duffield, in collaboration with Dr. Minlan Yu from Yale University, received the grant, which is titled “Distributed Approximate Packet Classification.” It is funded from 2016 to 2019 with a budget of $350,000.

Network traffic classification — assigning incoming packets to classes for processing based on pattern-matching rules — is critical for many network management tasks, including performance monitoring and fault diagnosis. However, as the number of classification tasks grows, the resources required to store and apply the rules, switch memory in particular, can become scarce. Duffield’s project takes an end-to-end view of traffic classification, observing that in addition to the memory usage at switches, other cheaper resources are involved in packet processing, specifically bandwidth to transfer selected packets to the receivers and downstream receivers that run applications. Trading off resources and even classification accuracy amongst these resources can lead to a better overall performance once the needs of downstream applications are factored in.

“The big research challenge now is how to realize these benefits in large and complex communications networks, such as in data centers, which can encompass millions of servers connected by hundreds of thousands of switches,” Duffield said.

Duffield, who also has a courtesy appointment in the Department of Computer Science and Engineering and is director of the Texas A&M Engineering Big Data Initiative, received his bachelor’s degree in natural sciences in 1982 and a master’s in mathematics in 1983 from the University of Cambridge. He received his Ph.D. in mathematical physics from the University of London in 1987. His research focuses on data and network science, particularly applications of probability, statistics, algorithms and machine learning to the acquisition, management and analysis of large datasets in communications networks and beyond.

Before joining the department, Duffield worked at AT&T Labs-Research, Florham Park, New Jersey, where he held the position of distinguished member of technical staff and was an AT&T Fellow. He previously held post-doctoral and faculty positions in Dublin, Ireland, and Heidelberg, Germany.

Duffield, the author of over 150 refereed journal and conference papers and inventor of 50 U.S patents, is co-inventor of the smart sampling technologies that lie at the heart of AT&T’s scalable Traffic Analysis Service. He is specialty editor-in-chief for Big Data of the journal Frontiers in ICT and he was charter chair of the IETF working group on packet sampling. Duffield is an IEEE Fellow, an IET Fellow and serves on the board of directors of ACM SIGMETRICS. He is an associate member of the Oxford-Man Institute of Quantitative Finance. He is a Texas A&M principal investigator on the DARPA funded consortium DEDUCE: Distributed Enclave Defense Using Configurable Edges, and has received faculty research awards from Google and Intel.

Shiyan Hu, a former student from the Department of Electrical and Computer Engineering at Texas A&M University, was named editor-in-chief of the Institute of Technology’s (IET) newly launched journal, Cyber-Physical Systems: Theory & Application.

Cyber-Physical Systems (CPS) include smart washing machines, self-driving cars, medical devices and smart grid meters. As the digital world becomes more than handheld, researchers seek to get a better understanding of the interface between cyberspace and the tangible elements.

Hu is an expert in CPS and cybersecurity, and is director of Center for Cyber-Physical Systems at Michigan Tech Institute of Computer and Cybersystems. As founding editor, Hu will lead a team of associate editors who are leading experts worldwide, including several from Carnegie Mellon, Stanford, the University of Illinois, National Taiwan University and The University of Tokyo.

In the journal they will address the close interactions and feedback loop between cyber components (such as embedded sensing systems) and physical components (such as energy systems) in a system. The CPS research topics include smart energy systems, smart home/building/community/city, connected and autonomous vehicle systems and smart health.

Cyber-Physical Systems: Theory & Application is dedicated to all aspects of the fundamental and applied research in the design, implementation and operation of CPS systems, considering performance, energy, user experience, security, reliability, fault tolerance, flexibility and extensibility. Its scope also includes innovative big data analytics for cyber-physical systems such as large-scale analytical modeling, complex stochastic optimization, statistical machine learning, formal methods and verification and real-time intelligent control, which are all critical to the success of CPS developments.

As an elected Fellow of IET, Hu leads this journal and also chairs the IEEE Technical Committee on Cyber-Physical Systems (www.ieee-cps.org), an authoritative constituency overseeing all CPS related activities within IEEE. He has published more than 100 research papers (about 30 in the premier IEEE Transactions), received numerous awards recognizing his research impact to the field and served as associate editor or guest editor for seven IEEE/ACM Transactions.

IET is the largest engineering society in Europe with more than 180,000 members. Visit Cyber-Physical Systems: Theory & Application.