A multi-strategy enhanced salp swarm algorithm for global optimization

As a typical nature-inspired swarm intelligence algorithm, because of the simple framework and good optimization performance, salp swarm algorithm (SSA) has been extensively applied to a lot of practical problems. Nevertheless, when facing a number of complicated optimization problems, particularly the high dimensionality and multi-dimensional problems, SSA will come to stagnation and decrease the optimal performance. To tackle this problem, this paper presents an enhanced SSA (ESSA) in which several strategies, including orthogonal learning, quadratic interpolation, and generalized oppositional learning are embedded to boost the global exploration and local exploitation performance of SSA. Orthogonal learning can help the worse salp break away from local optima, while quadratic interpolation is utilized to improve the accuracy of the global optimal through local search near the globally optimal solution. Also, generalized oppositional learning is used to improve the population quality through the initialization step and generation jumping. These strategies work together to assist SSA in promoting convergence performance. At the last CEC2017 benchmark suite and CEC2011, a real-world optimization benchmark is employed to estimate the property of ESSA in dealing with the high dimensionality and multi-dimensional problems. Three constrained engineering optimization problems are also used to assess the capability of ESSA in tackling practical engineering application problems. The experimental results and responding analysis make clear that the presented algorithm significantly outperforms the original SSA and other state-of-the-art methods.