Estimation of particle swarm distribution algorithms: Combining the benefits of PSO and EDAs

This paper presents a novel framework of the estimation of particle swarm distribution algorithms (EPSDAs). The aim is to effectively combine particle swarm optimization (PSO) with the estimation of distribution algorithms (EDAs) without losing their unique features. This aim is achieved by incorporating the following mechanisms: (1) selection is applied to the local best solutions in order to obtain more promising individuals for model building, (2) a probabilistic model of the problem is built from the selected solutions, and (3) new individuals are generated by a stochastic combination of the EDA's model sampling method and the PSO's particle moving mechanism. To exhibit the utility of the EPSDA framework, an extended compact particle swarm optimization (EcPSO) is developed by combining the strengths of the extended compact genetic algorithm (EcGA) with binary PSO (BPSO), along the lines of the suggested framework. Due to its effective nature of harmonizing the global search of EcGA with the local search of BPSO, EcPSO is able to discover the optimal solution in a fast and reliable manner. Experimental results on artificial to real-world problems have adduced grounds for the effectiveness of the proposed approach.