News | People | Our Github

seeRemote - Remote Visualization


As an enabling technology, remote visualization is crucial to the success of applications requiring collaborations among geographically separated users. Research in remote visualization is intriguing as well as challenging, due to the need for expertise in an array of different fields. Those include visualization and graphics, networking, distributed computing, and performance modeling.

For example. While many researchers have developed innovative algorithms for remote visualization, previous work has focused little on systematically investigating optimal configurations of remote visualization architectures. In this paper, we study caching and prefetching, an important aspect of such architecture design, in order to optimize the fetch time in a remote visualization system. Unlike a processor cache indexed by monolithic memory addresses, caching for remote visualization is unique and complex. We have discovered, through actual experimentation and numerical simulation, ways to systematically evaluate and search for optimal configurations of remote visualization caches under various scenarios, such as different network speeds, sizes of data for user requests, prefetch schemes, cache depletion schemes, etc. Based on our findings, we design a practical infrastructure software to adaptively optimize the caching architecture of general remote visualization systems, whenever a different application is started or the network throughput varies. The lower bound of achievable latency discovered with our approach can also aid the design of remote visualization algorithms and the selection of suitable network layouts for a remote visualization system.

This approach of taking a formal optimization point of view towards remote visualization also applies when general computation is also considered as part of the pipeline. Hence our follow-up work on adaptive pipeline re-configuration in remote settings.

'Remote Visualization by Browsing Image Based Databases with Logistical Networking', J. Ding, J. Huang, M. Beck, S. Liu, T. Moore and S. Soltesz, Proc. of SC2003 Conference, Phoenix, AZ, November, 2003.

'A Multi-Level Cache Model for Run-Time Optimization of Remote Visualization', Robert Sisneros, Chad Jones, Jian Huang, Jinzhu Gao, Byung-Hoon Park and Nagiza Samatova, IEEE Transactions on Visualization and Computer Graphics, 13(5), pp. 991-1003, 2007.

'Self-Adaptive Pipeline Configuration for Remote Visualization', Q. Wu, J. Gao, M. Zhu, N. Rao, J. Huang and S. Iyengar, submitted to IEEE Transactions on Visualization and Computer Graphics, 57(1), pp. 55-68, 2008.