Hybridizing particle filters and population-based metaheuristics for dynamic optimization problems

Many real-world optimization problems are dynamic. These problems require from powerful methods to adapt to problem modifications over time. Most applied research on metaheuristics has focused on static (non-changing) optimization problems and these methods often lack from adaptation strategies. Particle filters are sequential Monte Carlo estimation methods which can be applied to Bayesian filtering for nonlinear and non-Gaussian discrete-time dynamic models. In this paper, we propose a general method to hybridize population-based metaheuristics (PBM) and particle filters (PF). The aim of this method is to naturally devise to effective hybrid algorithms to solve dynamic optimization problems by exploiting the benefits of both approaches. Derived algorithms cleverly combine PF and PBM frameworks. As particular examples, two different effective algorithms, named path relinking particle filter (PRPF) and scatter search particle filter (SSPF) are respectively derived from the proposed hybridization method. Finally, efficient applications of these instantiated algorithms to different dynamic problems are also presented.