An Improved Particle Swarm Optimization Algorithm for Large-Scale Optimization

Particle swarm optimization is an optimization algorithm for swarm intelligence by observing the behavior of groups in nature. It simulates resource sharing and team cooperation among individuals in a group and is widely used because of its simple operation, fast running speed, and high precision. To overcome these shortcomings, this paper proposes an optimized particle swarm optimization algorithm to enhance its performance, which is called IPSOD. Compared with the original Particle swarm optimization, this paper first reduces the influence of the setting parameters by removing the acceleration coefficient and replacing the learning factor. Afterwards introducing noise-based disturbance into the Particle Swarm Optimization (PSO) algorithm can help particles escape local optima and explore a broader search space. Finally, the performance of IPSOD is tested by using a lot of benchmark functions. The experimental results show that the algorithm performs well in computation precision and convergence speed.