Distributed Simulation on the Grid: Opportunities and Challenges


Stephen John Turner


Parallel and Distributed Computing Centre,

Nanyang Technological University, Singapore 639798

Email: steve@pmail.ntu.edu.sg



The development of many complex simulation applications requires collaborative effort from researchers with different domain knowledge and expertise, possibly at different locations. These simulation systems often require large amounts of computing resources and data sets which may be geographically distributed. In order to support collaborative model development and to cater for the increasing complexity of such systems, it is necessary to harness distributed resources over the Internet. The emergence of Grid technologies provides exciting new opportunities for large scale distributed simulation, enabling collaboration and the use of distributed computing resources, while also facilitating access to geographically distributed data sets.

The last decade has seen an explosion of interest and innovation in the field of large scale distributed simulation. This activity is mainly centered on the High Level Architecture (HLA) [3], an IEEE standard to facilitate interoperability and reuse of simulation models. Using the HLA, and its associated middleware, the Run Time Infrastructure (RTI), a distributed simulation can be constructed by linking together a number of simulation components (or federates) into an overall simulation (or federation).

Traditionally, HLA-based distributed simulations are conducted using a vendor-specific RTI software. To run a distributed simulation over a WAN, the required software and hardware resource arrangements and security settings must be made before the actual simulation execution. Because of this inflexibility, it is not easy to run HLA-based distributed simulations across administrative domains. To address these inflexibility issues and leverage globally pervasive resources for distributed simulations, the Grid is naturally considered as a solution.

Grid computing was proposed by Foster as flexible, secure and coordinated resource sharing among dynamic collections of individuals, institutions and resources [1]. Three approaches can be defined for HLA-based distributed simulation on the Grid [4], namely a Grid-facilitated approach, a Grid-enabled approach and a Grid-oriented approach.

In the Grid-facilitated approach, Grid services are defined to facilitate the execution of HLA-based distributed simulations while the actual simulation communications are through a vendor-specific RTI. In the Grid-enabled approach, a client federate communicates with a federate server using Grid (or web) services and the federate server representing the client joins an HLA-based distributed simulation using a vendor-specific RTI. In the Grid-oriented approach, the RTI itself is implemented using Grid services according to the HLA standard. All communications are through Grid service invocations. This approach was raised in Fox's keynote at DS-RT 2005 [2].

This talk describes the opportunities offered by executing distributed simulations in a Grid environment and discusses the research challenges that must be addressed before these opportunities can be fully exploited.It presents a conceptual framework for the next generation of Grid-based distributed simulations and describes SOHR [4], a Service Oriented HLA RTI framework that implements the RTI entirely using Grid services following the Grid-oriented approach.




[1] I. Foster, C. Kesselman and S. Tuecke, 2001. The Anatomy of the Grid: Enabling Scalable Virtual Organizations. International Journal of High Performance Computing Applications, 15, 3, pp 200-222.

[2] G. Fox, A. Ho, S. Pallickara, M. Pierce and W. Wu, 2005. Grids for the GiG and Real Time Simulations. Proc. 9th IEEE International Symposium on Distributed Simulation and Real Time Applications, pp 129-138.

[3] IEEE, 2000. IEEE 1516 Standard for Modeling and Simulation-High Level Architecture.

[4] K. Pan, S.J. Turner, W. Cai, and Z. Li, 2007. A Service Oriented HLA RTI on the Grid. Proc. 2007 International Conference on Web Services, pp 984-992.




Stephen John Turner is Professor of Computer Science and Director of the Parallel and Distributed Computing Centre at Nanyang Technological University (Singapore). He received his MA in Mathematics and Computer Science from Cambridge University (UK) and his MSc and PhD in Computer Science from Manchester University (UK). His current research interests include: Parallel and Distributed Simulation, Grid Computing, High Performance Computing and Multi-Agent Systems. He is steering committee chair of the Principles of Advanced and Distributed Simulation (PADS) conference and advisory committee member of the Distributed Simulation and Real Time Applications (DS-RT) symposium. He is also an area editor for ACM Transactions on Modeling and Computer Simulation (TOMACS). He has published extensively on distributed simulation and has received a number of best paper awards at international conferences for his research in this area.

e-Merging Realities


Dr. Thomas A. Furness III


Professor & International Director

Human Interface Technology Laboratory
University of Washington
Seattle, WA 98195

Web: http://www.hitl.washington.edu

Web: http://http://www.hitlabnz.org


Over a career of 42 years, Prof. Furness has been exploring and developing technology tools for getting bandwidth to the brain and between brains. His work has encompassed fighter cockpits, virtual reality, retinal displays, educational tools, medical simulators, pain, phobias, molecular modeling, scanning fiber endoscopes and entertainment systems. This quest has been punctuated with side trips and aha experiences that have led to unanticipated destinations, many of which have involved distributed and real-time simulation. Dr. Furness plans to talk about lessons learned on his journey including unexpected delight with an aim to inspire, entertain and challenge conference attendees.



Prof. Furness is a pioneer in human interface technology and virtual reality. He received the BS degree in Electrical Engineering from Duke University and the Ph.D. in Engineering and Applied Science from the University of Southampton, England. Dr. Furness is currently a professor of Industrial Engineering with adjunct professorships in Electrical Engineering, Mechanical Engineering, Aeronautics and Astronautics, and Technical Communication at the University of Washington. He is the founder of the Human Interface Technology Laboratory (HIT Lab) at UW and founder and international director of the HIT Lab NZ at the University of Canterbury, Christchurch, NZ and the HIT Lab Australia at the University of Tasmania. He is also an Erskine Fellow and Adjunct Professor at the University of Canterbury.

Prior to joining the faculty at the University of Washington, Prof. Furness served a combined 23 years as an Air Force officer and civilian at the Armstrong Laboratory at Wright-Patterson Air Force Base, Ohio, where he developed advanced cockpits and virtual interfaces for the Department of Defense. He is the author of the Super Cockpit program and served as the Chief of Visual Display Systems and Super Cockpit Director until he joined the University of Washington in 1989.

Dr. Furness lectures widely and has appeared in many national and international network and syndicated television science and technology documentaries and news programs. He is the inventor of the personal eyewear display, the virtual retinal display, the HALO display and holds 15 patents in advanced sensor, display and interface technologies. With his colleagues Dr. Furness has started 24 companies, two of which are traded on NASDAQ at a market capitalization of > $ 2 B. In 1998 he received the Discover Award for his invention of the virtual retinal display.