DocumentCode :
375453
Title :
An evolutionary and adaptive approach for n-version programming
Author :
Grosspietsch, K.E. ; Romanovsky, A.
Author_Institution :
German Nat. Res. Center for Inf. Technol., St. Augustin, Germany
fYear :
2001
fDate :
2001
Firstpage :
182
Lastpage :
189
Abstract :
In this paper a concept is described to further improve the dependability characteristics of n-version systems. As one part of this strategy, we introduce an adaptive version management scheme. It is based on the use of dynamically changeable weight factors associated to the different versions of the system. Additionally, we propose to use a specific evolutionary scheme of design diversity combining n-version programming with genetic algorithms. Moreover, an additionally introduced segmentation scheme allows the combination of this strategy with recovery approaches
Keywords :
configuration management; genetic algorithms; programming; redundancy; software fault tolerance; GA; adaptive version management scheme; dependability characteristics; design diversity; dynamically changeable weight factors; evolutionary approach; genetic algorithms; multiversion programming; n-version programming; segmentation scheme; Algorithm design and analysis; Application software; Computer bugs; Costs; Genetic algorithms; Genetic programming; Information technology; Software design; Software engineering; Writing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Euromicro Conference, 2001. Proceedings. 27th
Conference_Location :
Warsaw
ISSN :
1089-6503
Print_ISBN :
0-7695-1236-4
Type :
conf
DOI :
10.1109/EURMIC.2001.952453
Filename :
952453
Link To Document :
بازگشت