Multi‐swarm competitive swarm optimizer for large‐scale optimization by entropy‐assisted diversity measurement and management

Abstract

As a crucial factor, population diversity greatly affects performances of swarm intelligence algorithms. Especially, for large‐scale optimization problems (LSOPs), the searching space is huge and the number of local optima dramatically increases. Hence to well address LSOPs, a healthy population diversity is helpful to prevent a swarm from premature convergence. However, this is a big challenge to balance exploration and exploitation for swarm intelligence algorithms. To handle with this issue, in this paper, we design a novel algorithm structure for swarm update. In the proposed algorithm, a swarm is divided into several groups and conduct competition in each group where the loser will learn from the winner and meanwhile the winner does nothing in the corresponding iteration. For diversity measurement, we abandon the distance‐based measurement, but employ a frequency‐based measurement, namely entropy indicator, so that the diversity maintenance can be conducted with a different measurement of convergence situation. In this way, the diversity maintenance and convergence can be conducted simultaneously and independently. The benchmarks on the suite of LSOPs are employed to validate the performance of a proposed algorithm. By comparing several state‐of‐the‐art competitor algorithms, the results demonstrate that the proposed algorithm is effective and competitive in dealing with LSOPs.