Safety critical software process improvement by multi-objective optimization algorithms

被引：0
作者：
Brito, Mario [1 ]
May, John [1 ]
机构：
[1] Univ Bristol, Safety Syst Res Ctr, Queens Bldg, Bristol BS8 1TR, Avon, England
来源：
SOFTWARE PROCESS DYNAMICS AND AGILITY, PROCEEDINGS | 2007年 / 4470卷
关键词：
software safety standards; Bayesian belief networks; genetic algorithms;
D O I：
暂无
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
One of the main concerns in safety critical software development is to identify a path through the software development lifecycle that will allow the software artefact to meet the target safety integrity level (SIL) at an acceptable cost. In our previous work we modelled aspects of the software development process recommended by IEC61508-3 software safety standard. In general, there are a number of paths that one can follow in order to comply with a target SIL. The path that one chooses to follow will undoubtedly effect the costs of the software development. In this paper we study a series of optimization algorithms that can be used to improve the software development process by optimization of two objectives, development costs and confidence in claimable integrity. Our analyses show that the non-dominated sorting genetic algorithm (NSGA) is the best performing algorithm in the search for these optimal processes.
引用
收藏
页码：96 / +
页数：2
相关论文
共 19 条
  • [1] Aarts E., 1989, Wiley-Interscience Series in Discrete Mathematics and Optimization
  • [2] [Anonymous], 1988, PROBABILISTIC REASON, DOI DOI 10.1016/C2009-0-27609-4
  • [3] Brito M, 2006, LECT NOTES COMPUT SC, V4166, P113
  • [4] DELIC KA, 1997, P DCCA 6 6 IFIP INT
  • [5] Fenton N., 1998, IEE Proceedings-Software, V145, P35, DOI 10.1049/ip-sen:19984895
  • [6] FONSECA CM, 1993, PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON GENETIC ALGORITHMS, P416
  • [7] Goldberg D.E, 1989, GENETIC ALGORITHMS S
  • [8] HALL P, 1992, P IFAC S ZUR SWITZ O, P239
  • [9] HORN J, 1994, P 1 IEEE C EV COMP, P82, DOI [DOI 10.1109/ICEC.1994.350037, 10.1109/ICEC.1994.350037]
  • [10] *HUG EXP AS, 1990, HUG API REF MAN VERS
12