A Hybrid Simplex Search and Modified Bare-bones Particle Swarm Optimization

In order to enhance global convergence capability of particle swarm optimization, this paper proposes a novel hybrid algorithm, called SMMBBPSO, based on the Nelder-Mead Simplex method (SM) and a Modified bare-bones particle swarm optimization (MBBPSO). In this algorithm, a new strategy based on K-means clustering is proposed to combine the powerful global search capability of MBBPSO and the high accurate local search capability of SM. This makes the proposed algorithm achieve a nice balance between exploitation and exploration capability. Meanwhile, an adaptive reinitialization strategy on inactive particles is proposed to help the swarm get away from local optimal positions. Finally, simulation results on benchmark functions demonstrate the effectiveness of the proposed algorithm.