Nian-Feng Tzeng
Center for Advanced Computer Studies
University of Louisiana at Lafayette
Different research topics have been pursued in this area, including
high-performance routers and switching fabrics, wireless communications and networks, and sensor networks.
They are outlined in sequence.
Current routers rely on enhanced software search algorithms or specific hardware support to meet the IP address lookup rate (of up to 5 million lookups per second per lookup unit), but a future high-speed network calls for routers with aggregate lookup rates of some two orders of magnitude higher than a lookup unit presently can offer. Hardware-assisted mechanisms for fast packet forwarding appear promising. In particular, the use of caches to hold lookup results can fulfill subsequent lookup requests for identical destinations immediately without resorting to FE's for lookups, reducing the mean lookup latency tremendously. Unlike other software- or hardware-based forwarding improvement approaches, our hardware-assisted mechanisms can be effectively applicable to both IPv6 and IPv4, ideally suitable for scalable high-performance routers.
A switching fabric connects line cards (LC's) of a router to provide paths
for packets to travel from arrival LC's to their respective departure LC's.
It dictates the scalability and the overall performance of the router.
We have pursued scalable switching fabrics with distributed packet routing
and low hardware complexity, realized via the multistage structure
whose adjacent stages are interconnected according to the indirect
n-cube connection style.
The proposed fabrics compare favorably with known multistage-based counterparts.
Minimum-cost data delivery in heterogeneous wireless networks under various constraints is pursued. Such a cost minimization problem is found to be NP-hard and its effective solution based on linear programming is developed. The very first range-free 3D localization we investigate depends solely on RFID tags and readers without other devices or sensors. It avoids the need of distance estimation according to received wireless signal strength or phase difference, for accurate 3D localization.
Age of Information (AoI) in multi-hop wireless networks measures information updating timeliness,
and its optimization is crucial for emerging applications that calls for punctual responses.
Our study explores inherent relationships between AoI and throughput in multi-hop networks,
characterizing both information freshness and the transmission speed, for the first time.
It tackles AoI and throughput optimization with routing-awareness, uncovering the entire landscape of
achievable throughput and AoI tradeoffs for selecting the best routing decision in a given application.
We further consider multi-hop networks with the OFDM (orthogonal frequency-division multiplexing) spectrum access
to arrive at optimized AoI at destination nodes.
Multicast has evolved into one of the most interesting Internet service but is yet to receive widespread deployment by service providers. This project investigates into a highly scalable multicast structure and several critical issues related to multicast scalability, in an attempt to help advance the state-of-the-art of multicast technologies and to enable large multicast applications that otherwise cannot be realized in the Internet. The considered scalable multicast framework achieves high scalability by means of a two-tier approach, where a component in the lower tier consists of group members within an Autonomous System (AS) and is constructed according to any known shared-tree-based multicast protocol (like CBT, bi-directional PIM-SM, or SM). It includes protocol development and implementation, design and evaluation of hardware multicast support, technology demonstration, and preparation of Internet RFC's.
