Jason Liu

Research Areas:

High-performance simulation and modeling, computer networks, computer systems, parallel and distributed computing.

Research Interests:

Dr. Liu is interested in applying advanced modeling and simulation techniques to large-scale complex discrete-event systems, including computer networks, computer systems, transportation networks, and biological systems. Part of his research involves in applying parallel computing techniques to handle large-scale discrete-event simulation models. His recent research is focused on combining parallel simulation and mathematical modeling techniques to improve the performance of large-scale computer network simulations.

Research Projects:

Parallel Real-time Immersive network Modeling Environment (PRIME) aims to investigate fundamental technologies that enable real-time large-scale network simulations and to develop a real-time immersive network simulation environment. Real-time network simulation combines the advantages of both simulation and emulation by running simulation models that interact with the physical world. Immersive large-scale network simulation requires that the simulation not only capture important characteristics of the target global network, but also support seamless interactions with distributed applications in real time. We apply parallel simulation and combine discrete-event simulation with fluid-based traffic modeling technique to speed up network simulation. We investigate scalable emulation infrastructures for embedding real applications.

Aquatic Network Experimentation Testbed (AQUANET) is to address the problems involved in designing and implementing robust underwater acoustic networks (e.g., for environmental monitoring and resource exploration applications). The testbed will include (1) several accurate acoustic propagation and network models, (2) a number of popular underwater protocols and applications, (3) provisions to allow existing software code to execute on AQUANET's platform, and (4) visualization support to process large amounts of data quickly and clearly. In addition, AQUANET will incorporate facilities to allow a hybrid acoustic network that combines both simulation and real traffic.

Performance Realization, Evaluation, and Simulation Testbed for Applications with Grid Enablement (PRESTAGE) investigates network virtualization techniques for testing Grid applications. The testbed will be built upon advanced virtualization and Grid application enablement technologies to facilitate the development of large-scale scientific applications—in particular, hurricane simulation and visualization applications—to effectively benefit from the computational and storage capacity available in a shared cyber-infrastructure, which consists of a wide range of heterogeneous resources spread across different administrative domains. Superscaling Network Emulation investigates techniques for scaling up network emulations to thousands of real network applications interacting with a virtual network with hundreds of thousands of network entities and with realistic network traffic load. The project will investigate machine virtualization techniques and combine them with real-time network simulation.

A Distributed Virtual Testbed for High-Speed TCP Variants is a project that aims at creating a distributed virtual environment for prototyping, evaluating, and benchmarking new and existing high-speed TCP protocols.

Detailed information of the research projects can be found at http://www.cis.fiu.edu/prime/.