The last decade witnesses the explosive growth of the Internet traffic and emerging applications such as IPTV, VoIP, VoD, P2P sharing and Cloud Computing. The traffic growth demands an enormous amount of network bandwidth and power consumption, which poses a huge challenge to current Internet infrastructure. The focus of this project is to investigate a new switching paradigm called spectrum-sliced elastic optical path (SLICE) network. Instead of allocating fixed-size frequencies to each channel as traditional networks, SLICE employs the Orthogonal Frequency Division Multiplexing (OFDM) technologies by splitting the signal into multiple smaller sub-carriers that are then transmitted simultaneously at different frequencies to the receiver.

Intellectual Merit: The objective of this project is to develop novel SLICE schemes to efficiently accommodate the traffic and alleviate power consumption in the backbone networks. The study includes (i) efficient and flexible bandwidth management through elastic sub-carriers allocation; (ii) robust optical path establishment with a finer granularity to best accommodate the traffic requests; (iii) joint optimization of RSA and virtual network mapping to ease the ossification problem in current Internet; and (iv) energy-efficient allocation of the constrained SLICE resources. This work will result in theoretic analysis, practical algorithms, simulation tools and performance modeling, which can serve as useful guidelines, and provide insights for the design of next-generation Internet.

Broader Impacts: This research will advance the state-of-the-art knowledge about optical and future networks. The modeling and design techniques from this project are applicable to a wide range of networking technologies such as resources allocation, network virtualization and survivability. Some of the new protocols, algorithms, modeling and performance results can be practically adopted by the industry. By involving both undergraduate and graduate students in the research, incorporating research agenda into both undergraduate and graduate courses and disseminating the findings, the project will help train the future scientists and engineers in high demand fields.

Agency
National Science Foundation (NSF)
Institute
Division of Computer and Network Systems (CNS)
Type
Standard Grant (Standard)
Application #
1117229
Program Officer
Joseph Lyles
Project Start
Project End
Budget Start
2011-09-01
Budget End
2014-08-31
Support Year
Fiscal Year
2011
Total Cost
$197,723
Indirect Cost
Name
Georgia State University Research Foundation, Inc.
Department
Type
DUNS #
City
Atlanta
State
GA
Country
United States
Zip Code
30303