Simulation-based optimization for design parameter exploration in hybrid system: a defense system example

  • Authors:
  • Jeong Hee Hong;Kyung-Min Seo;Tag Gon Kim

  • Affiliations:
  • Department of Electrical Engineering, KAIST, Republic of Korea;Department of Electrical Engineering, KAIST, Republic of Korea;Department of Electrical Engineering, KAIST, Republic of Korea

  • Venue:
  • Simulation
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a method for solving the optimization problems that arise in hybrid systems. These systems are characterized by a combination of continuous and discrete event systems. The proposed method aims to find optimal design configurations that satisfy a goal performance. For exploring design parameter space, the proposed method integrates a metamodel and a metaheuristic method. The role of the metamodel is to give good initial candidates and reduced search space to the metaheuristic optimizer. On the other hand, the metaheuristic method improves the quality of the given candidates. This proposal also demonstrates a defense system that illustrates the practical application of the presented method. The optimization objective of the case study is to find the required operational capability configurations of a decoy that meet the desired measure of effectiveness. Through a comparison with a full search method, two metamodeling methods without the aid of metaheuristics and a metaheuristic method without the support of metamodels, we confirmed that the proposed method provides same high-quality solutions as those of the full search method at a small computational cost.