Particle Swarm Optimization Applied to the Dynamic Allocation Problem

Particle Swarm Optimization (PSO) is based on the analysis of emergent behavior of bird flocks. Though it was originally designed for continuous optimization, PSO has provided good results in some recent works when applied to static and discrete optimization problems. In this paper, the particle encoding scheme is based on permutations and the PSO algorithm is adapted to solve a real-world application (cabs-customers allocation) of the dynamic task assignment problem. In the proposed approach, as the optimal solution may change during the optimization process, different strategies to detect and react to changes are tested. The results show that combinations of traditional techniques achieve good solutions in tested instances defined with different sizes and scales of changes.