A general framework of surrogate-assisted evolutionary algorithms for solving computationally expensive constrained optimization problems

Abstract

The objective and constraints of expensive constrained optimization problems (ECOPs) are often evaluated using simulations with different computational costs. However, the existing algorithms always assume that both the objective and constraints can be simultaneously obtained after one expensive simulation, i.e., the most time-consuming one among the evaluations, based on parallel computing. This will affect the optimization efficiency since it is not necessary to call all the simulations of objective and constraints for each solution. Therefore, a general framework of surrogate-assisted evolutionary algorithms (GF-SAEAs) is proposed to adaptively arrange search strategies based on actual simulation cost differences. Specifically, all constraints are classified into several constraint levels by effectively quantifying the computational cost differences of objective and constraints, and a level-by-level feasible region-driven local search strategy is designed to locate potential sub-feasible regions for each constraint level. Then three different search mechanisms are employed to explore and exploit these located regions. Additionally, an adaptive population regeneration strategy is utilized to restart the algorithm and prevent premature convergence. In summary, GF-SAEAs can maintain a good balance between feasibility and convergence. Experimental studies on benchmark problems and two real-world cases show that GF-SAEAs performs better than other state-of-the-art algorithms.