A methodology towards virtualisation-based high performance simulation platform supporting multidisciplinary design of complex products

  • Authors:
  • Lei Ren;Lin Zhang;Fei Tao;XiaolongLuke Zhang;Yongliang Luo;Yabin Zhang

  • Affiliations:
  • School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, China;School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, China;School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, China;College of Information Sciences and Technology, Pennsylvania State University, University Park, PA, 16802, USA;School of Automation Science and Electrical Engineering, Beihang University, Beijing, 100191, China;Beijing Simulation Centre, Beijing, 100854, China

  • Venue:
  • Enterprise Information Systems - Information Integration Infrastructures Supporting Multidisciplinary Design Optimisation
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Multidisciplinary design of complex products leads to an increasing demand for high performance simulation HPS platforms. One great challenge is how to achieve high efficient utilisation of large-scale simulation resources in distributed and heterogeneous environments. This article reports a virtualisation-based methodology to realise a HPS platform. This research is driven by the issues concerning large-scale simulation resources deployment and complex simulation environment construction, efficient and transparent utilisation of fine-grained simulation resources and high reliable simulation with fault tolerance. A framework of virtualisation-based simulation platform VSIM is first proposed. Then the article investigates and discusses key approaches in VSIM, including simulation resources modelling, a method to automatically deploying simulation resources for dynamic construction of system environment, and a live migration mechanism in case of faults in run-time simulation. Furthermore, the proposed methodology is applied to a multidisciplinary design system for aircraft virtual prototyping and some experiments are conducted. The experimental results show that the proposed methodology can 1 significantly improve the utilisation of fine-grained simulation resources, 2 result in a great reduction in deployment time and an increased flexibility for simulation environment construction and 3achieve fault tolerant simulation.