A multiobjective evolutionary algorithm based on objective-space localization selection

• المؤلفون الرئيسيون: Zhou, Yuren, Chen, Zefeng, Huang, Zhengxin, Xiang, Yi
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2022
• الموضوعات: Engineering::Computer science and engineering; Evolutionary Algorithm; Irregular Pareto Front
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/162386
• المؤسسة: Nanyang Technological University

This article proposes a simple yet effective multiobjective evolutionary algorithm (EA) for dealing with problems with irregular Pareto front. The proposed algorithm does not need to deal with the issues of predefining weight vectors and calculating indicators in the search process. It is mainly based on the thought of adaptively selecting multiple promising search directions according to crowdedness information in local objective spaces. Concretely, the proposed algorithm attempts to dynamically delete an individual of poor quality until enough individuals survive into the next generation. In this environmental selection process, the proposed algorithm considers two or three individuals in the most crowded area, which is determined by the local information in objective space, according to a probability selection mechanism, and deletes the worst of them from the current population. Thus, these surviving individuals are representative of promising search directions. The performance of the proposed algorithm is verified and compared with seven state-of-the-art algorithms [including four general multi/many-objective EAs and three algorithms specially designed for dealing with problems with irregular Pareto-optimal front (PF)] on a variety of complicated problems with different numbers of objectives ranging from 2 to 15. Empirical results demonstrate that the proposed algorithm has a strong competitiveness power in terms of both the performance and the algorithm compactness, and it can well deal with different types of problems with irregular PF and problems with different numbers of objectives.