Hybrid PSOS Algorithm For Continuous ‎Optimization

Particle swarm optimization (PSO) is one of the practical metaheuristic algorithms which is applied for numerical global optimization. It benefits from the nature inspired swarm intelligence, but it suffers from a local optima problem. Recently, another nature inspired metaheuristic called Symbiotic Organisms Search (SOS) is proposed, which doesn't have any parameters to set at start. In this paper, the PSO and SOS algorithms are combined to produce a new hybrid metaheuristic algorithm for the global optimization problem, called PSOS. In this algorithm, a minimum number of the parameters are applied which prevent the trapping in local solutions and increase the success rate, and also the SOS interaction phases are modified. The proposed algorithm consists of the PSO and the SOS phases. The PSO phase gets the experiences for each appropriate solution and checks the neighbors for a better solution, and the SOS phase benefits from the gained experiences and performs symbiotic interaction update phases. Extensive experimental results showed that the PSOS outperforms both the PSO and SOS algorithms in terms of the convergence and success rates.