Speaker: Prof. CAI Wentong, Parallel and Distributed Systems Laboratory, School of Computer Engineering, Nanyang Technological University, Singapore
Time: 14:00-15:30, June 2, 2016
Venue: Room 310,Third Floor, Office Building, Software Campus
Host: Prof. LIU Weiguo
Title: LARGE-SCALE SIMULATION IN THE CLOUD: CHALLENGES AND OPPORTUNITIES
ABSTRACT: Scientific discovery involves the formulation of a hypothesis to explain the observed phenomena and the design and execution of experiments to test the hypothesis. In addition to theory and experimentation, it is now widely accepted that Modelling and Simulation (M&S) is the third pillar for scientific discovery. M&S has quickly become an indispensable scientific methodology for research and education in engineering and science and has a wide range of applications, especially in the areas of large-scale complex adaptive systems (e.g., city-wide traffic simulation, and socio-ecological system in sustainable city simulation), industry informatics (e.g., port operation simulation, and supply-chain logistic simulation), and health informatics (e.g., pandemic simulation, and health care management).
When simulation model becomes large, one important issue is how it can be divided into smaller pieces and executed on high performance computing (HPC) platforms. The “pay as you go” model offered by Cloud computing makes it possible for the general M&S community to access HPC platforms. However, Cloud computing comes with certain performance issues which may affect the efficient execution of simulations. In this talk, some fundamental concepts of parallel discrete event simulation (PDES) will be covered. Then, the factors that may affect the performance of PDES on the Cloud will be identified and issues that concern executing PDES on the Cloud will be discussed. Finally, a hierarchical resource management system to enhance simulation execution performance on the Cloud will be described.
BIOGRAPHY: CAI Wentong is a Professor in the School of Computer Engineering at Nanyang Technological University, Singapore. He received his Ph.D. in Computer Science from University of Exeter (UK) in 1991. His expertise is mainly in the areas of Modeling and Simulation (particularly, modeling and simulation of large-scale complex systems, and system support for distributed simulation and virtual environments) and Parallel and Distributed Computing (particularly, Cloud, Grid and Cluster computing). He has published extensively in these areas and has received a number of best paper awards at the international conferences for his research in distributed simulation. He is an associate editor of the ACM Transactions on Modeling and Computer Simulation (TOMACS) and an editor of the Future Generation Computer Systems (FGCS). He has chaired a number of international conferences. Most recent ones include: 2015 IEEE/ACM Symposium on Distributed Simulation and Real Time Applications (DS-RT 2015), 2014 IEEE International Conference on Cloud Computing Technology and Science (CloudCom 2014), 2013 International ICST Conference on Simulation Tools and Techniques (SIMUTools 2013), 2012 IEEE International Conference on Parallel and Distributed Systems (ICPADS 2012), and 2011 IEEE International Symposium on Modelling, Analysis and Simulation of Computer and Telecommunication Systems (MACOTS 2011).. His recent research is concerned with investigating approaches to speed-up and scale-up agent-based simulations and using agent-based modeling and simulation to develop systems for training, planning, and decision support.