Surrogate-assisted classification-collaboration differential evolution for expensive constrained optimization problems

Abstract Expensive Constrained Optimization Problems (ECOPs) widely exist in various scientific and industrial applications. Surrogate-Assisted Evolutionary Algorithms (SAEAs) have recently exhibited great ability in solving these expensive optimization problems. This paper proposes a Surrogate-Assisted Classification-Collaboration Differential Evolution (SACCDE) algorithm for ECOPs with inequality constraints. In SACCDE, the current population is classified into two subpopulations based on certain feasibility rules, and a classification-collaboration mutation operation is designed to generate multiple promising mutant solutions by not only using promising information in good solutions but also fully exploiting potential information hidden in bad solutions. Afterwards, the surrogate is utilized to identify the most promising offspring solution for accelerating the convergence speed. Furthermore, considering that the population diversity may decrease due to the excessive incorporation of greedy information brought by the classified solutions, a global search framework that can adaptively adjust the classification-collaboration mutation operation based on the iterative information is introduced for achieving an effective global search. Therefore, the proposed algorithm can strike a well balance between local and global search. The experimental results of SACCDE and other state-of-the-art algorithms demonstrate that the performance of SACCDE is highly competitive.