Particle-swarm algorithm coordinating the exploration and the exploitation
一种协调勘探和开采能力的粒子群算法

A novel particle-swarm optimization(PSO) algorithm which coordinates the exploration ability and the exploitation ability(EEPSO) is presented. This algorithm divides the population of the swarm into the evolutionary sub-swarm and the randomized sub-swarm. During the evolution, the randomized sub-swarm reinforces the global space-exploration ability of the PSO algorithm, and uses the multi-species evolution information to generate the best-result-value space, guiding the particles of the evolutionary sub-swarm to approach this space. In order to improve the convergence rate, the guidance will be effective only when the evolutionary sub-swarm particles are in the convergence status. This limits the diversity of the population swarm, preventing the reduction in exploitation ability. The comparison experiments have been made between the proposed approach with the dissipative PSO and other cooperative particle swarm algorithm. The experimental results show that the proposed method not only effectively solves the premature convergence problem, but also significantly speeds up the convergence and improves the stability.