A Self-learning Bare-Bones Particle Swarms Optimization Algorithm

Abstract

In order to solve the premature convergence of BBPSO, this paper proposes a self-learning BBPSO (SLBBPSO) to improve the exploration ability of BBPSO. First, the expectation of Gaussian distribution in the updating equation is controlled by an adaptive factor, which makes particles emphasize on the exploration in earlier stage and the convergence in later stage. Second, SLBBPSO adopts a novel mutation to the personal best position ($Pbest$) and the global best position ($Gbest$), which helps the algorithm jump out of the local optimum. Finally, when particles are in the stagnant status, the variance of Gaussian distribution is assigned an adaptive value. Simulations show that SLBBPSO has excellent optimization ability in the classical benchmark functions.

This work was supported by National Natural Science Foundation of China under Grant Nos.61300059. Provincial Project of Natural Science Research for Anhui Colleges of China (KJ2012Z031, KJ2012Z024).