Adapting Particle Swarm Optimizationto Dynamic Environments
Anthony Jack Carlisle, Gerry Vernon Dozier · 2001
In this paper the authors propose a method for adapting the particle swarm optimizer for dynamic environments. The process consists of causing each particle to reset its record of its best position as the environment changes, to avoid making direction and velocity decisions on the basis of outdated information. Two methods for initiating this process are examined: periodic resetting, based on the iteration count, and triggered resetting, based on the magnitude of the change in the environment. These preliminary results suggest that these two modifications allow PSO to search in both static and dynamic