Kriging-assisted indicator-based evolutionary algorithm for expensive multi-objective optimization

Abstract

Selection mechanisms based on performance indicators are popular for solving multi-objective optimization problems (MOPs), which can provide a comprehensive evaluation of the convergence and diversity of candidate solutions. However, these mechanisms recently encounter difficulties when tackling computationally expensive MOPs attributed to the restricted quantity of real function evaluations. To tackle this problem, this paper proposes a Kriging-assisted indicator-based evolutionary algorithm. The primary concept is to utilize the Kriging model to approximate computationally expensive objective functions, thereby reducing the computational cost, and to employ the R2 indicator to assess the quality of candidate solutions. In addition, a dual selection mechanism based on the lower confidence bound is proposed as the model management strategy to balance exploration and exploitation. The experimental results demonstrate that the proposed algorithm is competitive when compared to five representative algorithms.