Search

Abstract This paper proposes a push and pull search (PPS) framework for solving constrained multi-objective optimization problems (CMOPs). To be more specific, the proposed PPS divides the search process into two different stages: push and pull search stages. In the push stage, a multi-objective evolutionary algorithm (MOEA) is used to explore the search space without considering any constraints, which can help to get across infeasible regions very quickly and to approach the unconstrained Pareto front. Furthermore, the landscape of CMOPs with constraints can be probed and estimated in the push stage, which can be utilized to conduct the parameter setting for the constraint-handling approaches to be applied in the pull stage. Then, a modified form of a constrained multi-objective evolutionary algorithm (CMOEA), with improved epsilon constraint-handling, is applied to pull the infeasible individuals achieved in the push stage to the feasible and non-dominated regions. To evaluate the performance regarding convergence and diversity, a set of benchmark CMOPs and a real-world optimization problem are used to test the proposed PPS (PPS-MOEA/D) and state-of-the-art CMOEAs, including MOEA/D-IEpsilon, MOEA/D-Epsilon, MOEA/D-CDP, MOEA/D-SR, C-MOEA/D and NSGA-II-CDP. The comprehensive experimental results show that the proposed PPS-MOEA/D achieves significantly better performance than the other six CMOEAs on most of the tested problems, which indicates the superiority of the proposed PPS method for solving CMOPs. [ABSTRACT FROM AUTHOR]

In this paper, we propose two multi-objective memetic algorithms (MOMAs) using two different adaptive mechanisms to address combinatorial optimization problems (COPs). One mechanism adaptively selects solutions for local search based on the solutions' convergence toward the Pareto front. The second adaptive mechanism uses the convergence and diversity information of an external set (dominance archive), to guide the selection of promising solutions for local search. In addition, simulated annealing is integrated in this framework as the local refinement process. The multi-objective memetic algorithms with the two adaptive schemes (called uMOMA-SA and aMOMA-SA) are tested on two COPs and compared with some well-known multi-objective evolutionary algorithms. Experimental results suggest that uMOMA-SA and aMOMA-SA outperform the other algorithms with which they are compared. The effects of the two adaptive mechanisms are also investigated in the paper. In addition, uMOMA-SA and aMOMA-SA are compared with three single-objective and three multi-objective optimization approaches on software next release problems using real instances mined from bug repositories (Xuan et al. IEEE Trans Softw Eng 38(5):1195-1212, 2012). The results show that these multi-objective optimization approaches perform better than these single-objective ones, in general, and that aMOMA-SA has the best performance among all the approaches compared. [ABSTRACT FROM AUTHOR]

Domination-based sorting and decomposition are two basic strategies used in multiobjective evolutionary optimization. This paper proposes a hybrid multiobjective evolutionary algorithm integrating these two different strategies for combinatorial optimization problems with two or three objectives. The proposed algorithm works with an internal (working) population and an external archive. It uses a decomposition-based strategy for evolving its working population and uses a domination-based sorting for maintaining the external archive. Information extracted from the external archive is used to decide which search regions should be searched at each generation. In such a way, the domination-based sorting and the decomposition strategy can complement each other. In our experimental studies, the proposed algorithm is compared with a domination-based approach, a decomposition-based one, and one of its enhanced variants on two well-known multiobjective combinatorial optimization problems. Experimental results show that our proposed algorithm outperforms other approaches. The effects of the external archive in the proposed algorithm are also investigated and discussed. [ABSTRACT FROM PUBLISHER]

This paper presents a novel memetic algorithm, named as IWO_DE, to tackle constrained numerical and engineering optimization problems. In the proposed method, invasive weed optimization (IWO), which possesses the characteristics of adaptation required in memetic algorithm, is firstly considered as a local refinement procedure to adaptively exploit local regions around solutions with high fitness. On the other hand, differential evolution (DE) is introduced as the global search model to explore more promising global area. To accommodate the hybrid method with the task of constrained optimization, an adaptive weighted sum fitness assignment and polynomial distribution are adopted for the reproduction and the local dispersal process of IWO, respectively. The efficiency and effectiveness of the proposed approach are tested on 13 well-known benchmark test functions. Besides, our proposed IWO_DE is applied to four well-known engineering optimization problems. Experimental results suggest that IWO_DE can successfully achieve optimal results and is very competitive compared with other state-of-art algorithms. [ABSTRACT FROM AUTHOR]