A Diversity-Guided Particle Swarm Optimizer for Dynamic Environments

For many real-world changeable problems over time, the goal of optimization is not only to acquire an optimal solution, but also to track its progression through the search space as closely as possible. In this paper, an improved detection technique at the particle level is designed. Then, a new method of response, learning from the changing global optimum for new environments guided by population diversity, is designed. It defines response condition as well as part of particles to be reset and flying direction after a change. Then, the parabolic benchmark functions with various severities are used to test, compared with the Eberhart-PSO and APSO, and the results show the modified strategies are effective in tracking changes.