Adaptive neighbourhood size adjustment in MOEA/D-DRA

Abstract

Multi-objective optimisation algorithm based on decomposition (MOEA/D) is a well-known multi-objective optimisation algorithm, which was widely applied for solving multi-objective optimisation problems (MOPs). MOEA/D decomposes a multi-objective problem into a set of scalar single objective sub-problems using aggregation function and evolutionary operator. A further improved version of MOEA/D with dynamic resource allocation strategy (MOEA/D-DRA) has exhibited outstanding performance on CEC2009 in terms of the convergence. However, it is very sensitive to the neighbourhood size. In this paper, a new enchanted MOEA/D-ANA strategy based on the adaptive neighbourhood size adjustment (MOEA/D-ANA) was presented to increase the diversity, which mainly focuses on the solutions density around sub-problems. The experiment results demonstrate that MOEA/D-ANA performs the best compared with other five classical MOEAs on the CEC2009 test instances.