A new adaptive well-chosen inertia weight strategy to automatically harmonize global and local search ability in particle swarm optimization

摘要: The global search ability and local are two highly important components of particle swarm optimizer, which inconsistent each other in many cases, we proposed a novel inertia weight strategy that can adaptively select preferable decline curve for form curves the constructed function according to fitness value swarm, automatically harmonize ability, quicken convergence speed, avoid premature problem, obtain optimum. Experimental results on several benchmark functions show algorithm rapidly converge at very high quality solutions.