scholarly journals HLA-Transparent Distributed Simulation of Agent-based Systems

Author(s):  
Daniele Gianni ◽  
Andrea DAmbrogio ◽  
Giuseppe Iazeolla ◽  
Alessandra Pieroni
2007 ◽  
Vol 17 (3) ◽  
pp. 11 ◽  
Author(s):  
Michael Lees ◽  
Brian Logan ◽  
Georgios Theodoropoulos

Author(s):  
Yu-Cheng Chou ◽  
David Ko ◽  
Harry H. Cheng ◽  
Roger L. Davis ◽  
Bo Chen

Two challenging problems in the area of scientific computation are long computation time and large-scale, distributed, and diverse data sets. As the scale of science and engineering applications rapidly expands, these two problems become more manifest than ever. This paper presents the concept of Mobile Agent-based Computational Steering (MACS) for distributed simulation. The MACS allows users to apply new or modified algorithms to a running application by altering certain sections of the program code without the need of stopping the execution and recompiling the program code. The concept has been validated through an application for dynamic CFD data post processing. The validation results show that the MACS has a great potential to enhance productivity and data manageability of large-scale distributed computational systems.


Author(s):  
Michael Lees ◽  
Brian Logan ◽  
Ton Oguara ◽  
Georgios Theodoropoulos

2021 ◽  
Vol 16 (93) ◽  
pp. 93-108
Author(s):  
David E. Sorokin ◽  

The author of this article represents his own work DVCompute Simulator, which is a collection of general-purpose programming libraries for discrete event simulation. The aim of the research was to create a set of simulators in the Rust language, efficient in terms of speed of execution, based on a unified approach and destined for different simulation modes. The simulators implement such modes as ordinary sequential simulation, nested simulation and distributed simulation. The article describes that nested simulation is related to Theory of Games, while distributed simulation can be used for running large-scale simulation models on supercomputers. It is shown how these different simulation modes can be implemented based on the single approach that combines many paradigms: the event-oriented paradigm, the process-oriented one, blocks similar to the GPSS language and even partially agent-based modeling. The author's approach is based on using the functional programming techniques, where the simulation model is defined as a composition of computations. The results of testing two modules are provided, where the modules support both the optimistic and conservative methods of distributed simulation.


Sign in / Sign up

Export Citation Format

Share Document