Heterogeneous particle swarms in dynamic environments

This paper investigates the performance of a dynamic heterogeneous particle swarm optimizer (dHPSO) on dynamic unconstrained optimization problems. The results are compared to that of charged and quantum particle swarms, specifically designed for optimization in dynamic environments. It is shown that dHPSO possesses the ability to manage the diversity of the swarm dynamically, allowing it to overcome the problem of diversity loss and to successfully track a moving optimum over time. Additionally, it is shown that dHPSO is able to adapt to the size of the search domain without the need for parameter tuning. Experiments that are conducted on a range of dynamic problems show that dHPSO consistently produces lower average errors than charged and quantum swarms over 2000 iterations, suggesting that dHPSO is a suitable algorithm for optimization in dynamic environments.