Background: Tarek Abdelzaher


Bio: Tarek Abdelzaher received his B.Sc. and M.Sc. degrees in Electrical and Computer Engineering from Ain Shams University, Cairo, Egypt, in 1990 and 1994 respectively. He received his Ph.D. from the University of Michigan in 1999 on Quality of Service Adaptation in Real-Time Systems. He has been an Assistant Professor at the University of Virginia, where he founded the Software Predictability Group. He is currently a Professor and Willett Faculty Scholar at the Department of Computer Science, the University of Illinois at Urbana Champaign.

He has authored/coauthored more than 170 refereed publications in real-time computing, distributed systems, sensor networks, and control. He is an Editor-in-Chief of the Journal of Real-Time Systems, and has served as Associate Editor of the IEEE Transactions on Mobile Computing, IEEE Transactions on Parallel and Distributed Systems, IEEE Embedded Systems Letters, the ACM Transaction on Sensor Networks, and the Ad Hoc Networks Journal. He chaired (as Program or General Chair) several conferences in his area including RTAS, RTSS, IPSN, Sensys, DCoSS, ICDCS, and ICAC.
Abdelzaher’s research interests lie broadly in understanding and controlling performance and temporal properties of networked embedded and software systems in the face of increasing complexity, distribution, and degree of embedding in an external physical environment. Tarek Abdelzaher is a recipient of the IEEE Outstanding Technical Achievement
and Leadership Award in Real-time Systems (2012), the Xerox Award for Faculty Research (2011), as well as several best paper awards. He is a member of IEEE and ACM.

Abdelzaher is interested in application design on top of NDN. When names of data objects are a first-class abstraction, information on relations between different content objects is implicitly available to the network via their names. For example, names that share a longer prefix can be assumed to refer to more similar objects than names that share a shorter prefix. This relation offers a foundation for information-throughput maximization. Rather than optimizing mere bit throughput over the network, in NDN it becomes possible to optimize information transfer. The capability is critical to networks that suffer bottlenecks, such as tactical military networks, and mobile ad hoc networks arising in disaster-response scenarios. It is also important in scenarios where applications need only a representative sampling of content as opposed all content matching a query. In both cases, some form of “summarization” is needed, which can be accomplished in NDN in a generic and efficient fashion using algorithms that are only a function of content names and their relations in the hierarchical name space. Abdelzaher is interested in designing caching and forwarding algorithms for information-maximizing networks, as well as name spaces and applications that leverage these algorithms to achieve a better tradeoff between information quality and resource cost.

NDN Plans:
Two specific contributions that fall under information-throughput maximization in NDN are the information funnel and diversity cache. The information funnel is a novel transport-layer data collection protocol that maximizes a measure of delivered information utility. NDN, where data objects are named instead of hosts, is especially suited for utility-maximizing transport in resource-constrained environments, because data names can expose similarities between named objects that can be leveraged for minimizing redundancy, hence maximizing utility. With proper name space design, a transport protocol prioritizes transmission of data items over bottlenecks to maximize information utility, with very weak assumptions on the utility function. This prioritization is achieved merely by comparing data names, without knowing application-level name semantics, which makes it generalizable across a wide range of applications. Preliminary evaluation results (under submission) show that the information funnel improves the utility of the collected data objects compared to other state-of-the-art solutions.

Diversity caching explores the benefits of naming data for the design of information-maximizing caching policies in ad hoc networks. It is shown that the approach allows development of caching policies for ad hoc networks that simultaneously offer (i) better quality of information (in terms of coverage), (ii) higher throughput (in terms of responses per query), and (iii) lower latency.