Research on Function Optimization Based on Improved Genetic Particle Swarm Optimization

Abstract

Abstract Aiming at the shortcomings of single algorithm such as blind operation, directionless, long calculation time, low accuracy in Genetic Algorithm and poor diversity of population of Particle Swarm Optimization, which is prone to premature and fall into local optimum. In this study, the serial algorithm fusion idea is adopted, and the population evolved from the Genetic Algorithm is taken as the initial population to be executed by the Particle Swarm Algorithm, namely GAPSO algorithm. In view of the drawbacks of the respective algorithms in the execution of GAPSO algorithm, this paper proposes an Improved Genetic Particle Swarm Optimization algorithm, namely IGAPSO algorithm. In this algorithm, the improved GA only optimizes the initial particle once and then gives it to the improved PSO for optimization. Its optimization method and ability are greatly improved, resulting in a rapid increase in convergence speed. In addition, the improved PSO introduces adaptive inertia weight and learning factor, so that the particles can adaptively adjust global search and local search, and adaptively balance the influence of self-experience and social experience, which greatly avoids falling into local optimization problem and makes the solution more accurate. Through the verification of test functions, GAPSO has obviously improved the calculation accuracy, convergence speed and global stability compared with a single algorithm, while IGAPSO has also improved the convergence accuracy and speed compared with GAPSO, especially in multi-peak functions.