Constraint handling in NSGA-II for solving optimal testing resource allocation problems

Research output: Contribution to journalArticle

Authors

  • Guofu Zhang
  • Zhaopin Su
  • Feng Yue
  • Jianguo Jiang

Colleges, School and Institutes

External organisations

  • Hefei University of Technology
  • Southern University of Science and Technology

Abstract

In software testing, optimal testing resource allocation problems (OTRAPs) are important when seeking a good tradeoff between reliability, cost, and time with limited resources. There have been intensive studies of OTRAPs using multiobjective evolutionary algorithms (MOEAs), but little attention has been paid to the constraint handling. This paper comprehensively investigates the effect of the constraint handling on the performance of nondominated sorting genetic algorithm II (NSGA-II) for solving OTRAPs, from both theoretical and empirical perspectives. The heuristics for individual repairs are first proposed to handle constraint violations in NSGA-II, based on which several properties are derived. Additionally, the Z-score based Euclidean distance is adopted to estimate the difference between solutions. Finally, the above methods are evaluated and the experiments show several results. 1) The developed heuristics for constraint handling are better than the Existing Strategy in terms of the capacity and coverage values. 2) The Z-score operation obtains better diversity values and reduces repeated solutions. 3) The modified NSGA-II for OTRAPs (called NSGA-II-TRA) performs significantly better than the existing MOEAs in terms of capacity and coverage values, which suggests that NSGA-II-TRA could obtain more and higher quality testing-time-allocation schemes, especially for large, complex datasets. 4) NSGA-II-TRA is robust according to the sensitivity analysis results.

Details

Original languageEnglish
Pages (from-to)1193-1212
Number of pages20
JournalIEEE Transactions on Reliability
Volume66
Issue number4
Early online date31 Aug 2017
Publication statusE-pub ahead of print - 31 Aug 2017

Keywords

  • Software reliability, Testing-resource allocation, Multi-objective optimization, Constraint handling, Heuristics