Improved salp swarm algorithm based on gravitational search and multi-leader search strategies

Abstract

The salp swarm algorithm (SSA) will converge prematurely and fall into local optimum when solving complex high-dimensional multimodal optimization tasks. This paper proposes an improved SSA (GMLSSA) based on gravitational search and multi-swarm search strategies. In the gravitational search strategy, using multiple salp individuals to guide the location update of search agents can get rid of the limitation of individual guidance and improve the exploration ability of the algorithm. In the multi-swarm leader strategy, the original population is divided into several independent subgroups to increase population diversity and avoid falling into local optimization. In the experiment, 20 benchmark functions (including the well-known CEC 2014 function) were used to test the performance of the proposed GMLSSA in different dimensions, and the results were compared with the most advanced search algorithm and SSA variants. The experimental results are evaluated through four different analysis methods: numerical, stability, high-dimensional performance, and statistics. These results conclude that GMLSSA has better solution quality, convergence accuracy, and stability. In addition, GMLSSA is used to solve the tension/compression spring design problem (TCSD). The proposed GMLSSA is superior to other competitors in terms of solution quality, convergence accuracy, and stability.

Keywords

• salp swarm optimization
• gravitational search strategy
• multi-leader search strategy
• wilcoxon's rank-sum test
• tension/compression spring design problem