文献类型：期刊文献

英文题名：SMTIBEA: a hybrid multi-objective optimization algorithm for configuring large constrained software product lines

作者：Guo, Jianmei[1];Liang, Jia Hui[2];Shi, Kai[1];Yang, Dingyu[3];Zhang, Jingsong[4];Czarnecki, Krzysztof[2];Ganesh, Vijay[2];Yu, Huiqun[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China;[2]Univ Waterloo, Dept Elect & Comp Engn, Waterloo, ON, Canada;[3]Shanghai Dianji Univ, Sch Elect Informat, Shanghai, Peoples R China;[4]Chinese Acad Sci, Inst Biochem & Cell Biol, Inst Biol Sci, Shanghai, Peoples R China

年份：2019

卷号：18

期号：2

起止页码：1447

外文期刊名：SOFTWARE AND SYSTEMS MODELING

收录：;EI(收录号：20173003979613);WOS:【SCI-EXPANDED(收录号:WOS:000464022400030)】；

基金：We would like to thank anonymous reviewers for their helpful comments. This research was partially supported by Shanghai Municipal Natural Science Foundation (No. 17ZR1406900), Shanghai Pujiang Talent Program (No. 17PJ1401900), Specialized Fund of Shanghai MunicipalCommission of Economy and Informatization (No. 201602008), Specialized Research Fund forDoctoral Program of Higher Education (No. 20130074110015), National Natural Science Foundation of China (No. 61173048, 61602460), China Postdoctoral Science Foundation (No. 2016M600338), Natural Sciences and Engineering Research Council of Canada, and Pratt & Whitney Canada.

语种：英文

外文关键词：Software product lines; Search-based software engineering; Multi-objective evolutionary algorithms; Constraint solving; Feature models

摘要：A key challenge to software product line engineering is to explore a huge space of various products and to find optimal or near-optimal solutions that satisfy all predefined constraints and balance multiple often competing objectives. To address this challenge, we propose a hybrid multi-objective optimization algorithm called SMTIBEA that combines the indicator-based evolutionary algorithm (IBEA) with the satisfiability modulo theories (SMT) solving. We evaluated the proposed algorithm on five large, constrained, real-world SPLs. Compared to the state-of-the-art, our approach significantly extends the expressiveness of constraints and simultaneously achieves a comparable performance. Furthermore, we investigate the performance influence of the SMT solving on two evolutionary operators of the IBEA.