A Constrained Multiobjective Evolutionary Algorithm based on State Transition Strategy

Abstract

Constrained multiobjective problems (CMOPs) are often encountered in many real-world applications which is difficult to solve because the relationship between constraints and objectives is not well balanced. To more specific, complex constraints may cause algorithms trapped in local optimum or even cannot find the feasible region. Thus, the importance of constraint multiobjective evolutionary algorithms (CMOEAs) is how to deal with constraints. In order to handling CMOPs, this paper proposed a strategy to solve the CMOPs which is named state transition based on constraint (STC). By judging whether the search gets trapped in the local optimum or reaches the unconstrained pareto front in the process of optimization, STC can adjust the value to controlling constraint handling technique (CHT) that help evolution of the population. This STC strategy is embedded in decomposition evolutionary algorithm (MOEA/D). The algorithm is compared with three state-of-the-art constrained multiobjective evolutionary algorithms (CMOEAs) on 16 typical constrained benchmark problems. The experimental results show that the proposed algorithm can effectively tackle with CMOPs.