Differential evolution with level comparison for constrained optimization

  • Authors:

  • Ling-Po Li;Ling Wang;Ye Xu

  • Affiliations:

  • Tsinghua National Laboratory for Information Science and Technology, Department of Automation, Tsinghua University, Beijing, P.R. China;Tsinghua National Laboratory for Information Science and Technology, Department of Automation, Tsinghua University, Beijing, P.R. China;Tsinghua National Laboratory for Information Science and Technology, Department of Automation, Tsinghua University, Beijing, P.R. China

  • Venue:
  • ICIC'09 Proceedings of the Intelligent computing 5th international conference on Emerging intelligent computing technology and applications
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The effectiveness of a constrained optimization algorithm depends on both the searching technique and the way to handle constraints. In this paper, a differential evolution (DE) with level comparison is put forward to solve the constrained optimization problems. In particular, the α (comparison level) constrained method is adopted to handle constraints, while the DE-based evolutionary search is used to find promising solutions in the search space. In addition, the scale factor of the DE mutation is set to be a random number to vary the searching scale, and a certain percentage of population is replaced with random individuals to enrich the diversity of population and to avoid being trapped at local minima. Moreover, we let the level increase exponentially along with the searching process to stress feasibility of solution at later searching stage. Experiments and comparisons based on the 13 well-known benchmarks demonstrate that the proposed algorithm outperforms or is competitive to some typical state-of-art algorithms in terms of the quality and efficiency.