Particle swarm optimization for function optimization in noisy environment

As a novel evolutionary searching technique, particle swarm optimization (PSO) has gained wide research and effective applications in the field of function optimization. However, to the best of our knowledge, most studies based on PSO are aimed at deterministic optimization problems. In this paper, the performance of PSO for function optimization in noisy environment is investigated, and an effective hybrid PSO approach named PSOOHT is proposed. In the PSOOHT, the population-based search mechanism of PSO is applied for well exploration and exploitation, and the optimal computing budget allocation (OCBA) technique is used to allocate limited sampling budgets to provide reliable evaluation and identification for good particles. Meanwhile, hypothesis test (HT) is also applied in the hybrid approach to reserve good particles and to maintain the diversity of the swarm as well. Numerical simulations based on several well-known function benchmarks with noise are carried out, and the effect of noise magnitude is also investigated as well. The results and comparisons demonstrate the superiority of PSOOHT in terms of searching quality and robustness.